{"text": " meta just released its most capable ai model which is muse spark 1.1 and according to zag this is a model that can act it can watch a video use tools and get it as done for you not just answer questions and later in the video i'm going to talk about all of that mark zuckerberg actually the way he announced it on the x platform i think he came back on it after a few years and look at what he leads with a strong agentic and coding model at a very low price through our new meta model api a low price a paid api now think about this from a company that for years made free and open source ai its entire identity so before i get into what spark can actually do i think it'll be interesting to understand what pushed meta to change the strategy like this so let's go back to history and rewind right because the backstory explains everything for years meta was the champion of open source ai back in july 2024 zuck published an essay titled literally open source ai is the path forward free downloadable models were meta's whole identity and he positioned the company as the open alternator to closed labs like open ai then it changed fast meta brought in scale ai's alexander van as their chief ai officer a 14 billion dollar deal they stood up a brand new super intelligence lab and back in april shipped the first muke spark model which was closed no waits no download available that was a real break from open source for the first time right and meta's frontier model were locked behind its own doors running inside its apps instead of out in the open and this week meta took the next step a big upgrade muse spark 1.1 and for the first time ever a public paid api with pricing zuckerberg called very aggressive so meta didn't just close its best model it put a price tag on it and open it up for anyone to build it meta didn't just undercut everyone on price it's about a quarter of what gpt and claude cost they also made mu spark drop straight into the tools developers already use open ai setup sure but also clawed code anthropic's own coding tool you pointed at meta's model change basically one line and now you're suddenly running on muse spark at a quarter of the price meta built a side door out of open ai and anthropic and hung a discount sign on it this isn't just a new model it's a direct play for their rivals customers now two things to keep honest one llama isn't dead it's still open still downloadable what changes matters best models are closed now and two as wild as the flip feels it makes sense right matters spending north of a hundred billion dollars a year on ai you don't spend that and give your best model away and if you want a personal agent in the hands of three billion people you want to own the model doing the work so what did they actually build and is it worth your time i started using it for the last couple of days and i also built a little app on meta's model i handed it a video of anything that you probably want to sell and asked it to give me a full price ready to post listing on facebook's marketplace so that's one demo that we will see second i also ran it on clock course and tropic so that will be an interesting one and third i wanted to test the real multi-modality so i gave it a picture of the ingredients in the fridge and it was able to pinpoint the price tag on it right so i'll show you all of the fun parts as we go through but then interesting part as i mentioned earlier is meta shift to the paid strategy which is just keeping it open source all right before we dive deep into it a quick disclaimer all opinions are my own and do not belong to my employer all right with that let's get into it all right so one of the fastest ways to experience spark is to actually come to meta.ai and change the mode from instant to thinking mode so if you ask any question like for example here i'm asking which particular meta model are you using you would see that it is going to confirm that it is using spark 1.1 so you just need to change the mode to thinking and you will get to leverage the spark 1.1 model right so it was launched literally a couple of days back okay but then from a developer perspective if you want to use it you need to go into dev.meta.ai so here i am in dev.meta.ai and i was able to create an api key and you can already see detailed docs and how you're able to use this in plot code and these are all the details that they have provided codecs then if you want to just call it via python as well as curl right these are some of the details that have been given so what you could do is you can create an api key so what i did was as i mentioned earlier i'm going to be doing three different demos so the first demo here is think of it like a facebook marketplace listing generator so here i would be using muse park so what i'm going to do here is upload a video here so you can see the video very clearly this is a video of a bike of a kid where i've just taken like a very short nine seconds i just wanted to make it a little bit tough and i'm going to ask it to generate listing right so there are multiple things which are happening here right so obviously it is calling the muse spark 1.1 model so the first thing what's happening here is it is going to be identifying the item so this is the response back from the first step so it has correctly identified that this is a global primo pink three wheel kit scooter and obviously it is used so it has understood that as well so very good job done very quickly you can see the amount of time it took was very short then the agent is going to now do a pricing research so it's going to look into some other prices so that it can give us some comparison pricing right once you have that idea of the comparison pricing then it will consolidate all of that and create the listing so you can see that i'll search current resale listing for your global this in the us market it is around this and you can see all the pricing over here in uk it is something of this sort right in canada it is this right and because this is coming from meta and facebook so and this is marketplace api so you will be able to actually get the right because they already have the data so now it has already created the listing so you can clearly see that global primo pink three wheel kit scooter hot pink and black it also identified this the best for scooter for toddlers and kids this is condition is very good the retails for this but then here we are charging it at this particular price right so that's what it was able to do and you can see that it did a pretty good job and you were able to then copy this and just take it and paste it in in marketplace right so the reason i wanted to do this was to show you how you're able to create something like this very quickly using new spark and it really demonstrates an agentic behavior understanding of a multimodal input in this case video and also doing a quick search and then not only just limited to the us but also search across the board and then providing you like a competitive pricing right so i was very impressed with what i saw okay so that's that's the first demo i hope you enjoyed it now what i want to do here is i actually want to show you how you are also able to use it directly in claw code so for that let's just open clawed right so in this case i've already configured clods connector so if i show you this you can see that here i have got the new spark 1.1 agent here right so the way i was able to do this was i basically followed this specific instruction here i provided the api key which i already showed you and i ran this in powershell first right so before actually running clawed i basically ran this right so once i have this now clawed is being forced to use this particular model which is new spark 1.1 right so you are welcome to try this and see what kind of results you're getting all right so for the third demo i decided to actually use one of meta's cookbooks which they have given and they have really done a great job and provided 10 actually 13 different use cases so here in this one i actually decided to use this perception grounding right so the use case here is you have your fridge filled with some food objects and can meta's multimodal model be able to get and identify each one of the food objects and provide some sort of a score right so if i go in detail like this is the original image you can see all the different food items over here and once you basically run this particular program and provide your api key it should be able to identify each one of these items and provide the score right so what i did was i ran this particular prompt right i'm a pescetarian with high cholesterol put green dots on recommended food and now that it has run this particular output once i give this particular command i will be able to see the output right you can see it is now generating the html overlay so that it will be able to identify that right so i want to also show you the output of what it produces so again just for the reference this is how the original picture looks like right so if you look at this is how the picture looks like now what we will be able to generate is something like this which is after after it has generated the output right so pescetarian plus high cholesterol fridge guide recommended and not recommended and you can see the scores pretty much well done so this is the output and again thought like this was amazing because you can see orange juice we all think that it is great but for some reason it is giving not a great score so let's see if i eat something which is not recommended so cheese pack is not recommended yellow cheese is not recommended whereas this butter is definitely not recommended so pretty cool right so you are able to use this out of the box and able to get this label and it's fast it's cheaper as well so this is what i wanted to cover the main idea is a make you aware of this is a brand new agentic model out there so definitely give it a try you can see there like this is a good playground and a dashboard so i've been playing with it it provides like the usage and stuff like that very well etc all of those things and then they have also given like 20 free so so far i've ran it a few times and i only spent less than a dollar and there's another way for you to try which is playground so you can upload an image or ask certain questions you can also change some of the settings over here and then there are some advanced settings as well right you can add some json schema and stuff like that so what i would recommend is give it a shot also try it in a cop in combination with clock code the app that i built i asked anti-gravity to actually build the app but leveraging the spark api you could do like all of these types of combination where you use your id and build an app like this and see for yourself what you feel as the performance right and obviously on the benchmarks they have talked about the benchmarks over here they've compared themselves against gemini 3.1 4.8 these are here for your reading and i will share this as well of course does all different types of use cases from an agentic perspective it also does computer use it definitely writes code all of these things are something which which they have actually explained right so multimodal is something which we saw live again hopefully this was helpful it added some extra knowledge to your existing knowledge base let me know if you guys have any questions and what do you feel after trying this thank you very much for your time if you like the video please hit that like button and if you're new here please hit that subscribe button as well thank you for watching and i will see you in the next one", "segments": [{"id": 0, "seek": 0, "start": 0.0, "end": 6.8, "text": " meta just released its most capable ai model which is muse spark 1.1 and according to zag this is a", "tokens": [50365, 19616, 445, 4736, 1080, 881, 8189, 9783, 2316, 597, 307, 39138, 9908, 502, 13, 16, 293, 4650, 281, 27001, 341, 307, 257, 50705], "temperature": 0, "avg_logprob": -0.04963681253336244, "compression_ratio": 1.7107142857142856, "no_speech_prob": 2.1932388630935273e-12}, {"id": 1, "seek": 0, "start": 6.8, "end": 12.86, "text": " model that can act it can watch a video use tools and get it as done for you not just answer", "tokens": [50705, 2316, 300, 393, 605, 309, 393, 1159, 257, 960, 764, 3873, 293, 483, 309, 382, 1096, 337, 291, 406, 445, 1867, 51008], "temperature": 0, "avg_logprob": -0.04963681253336244, "compression_ratio": 1.7107142857142856, "no_speech_prob": 2.1932388630935273e-12}, {"id": 2, "seek": 0, "start": 12.86, "end": 16.8, "text": " questions and later in the video i'm going to talk about all of that mark zuckerberg actually", "tokens": [51008, 1651, 293, 1780, 294, 264, 960, 741, 478, 516, 281, 751, 466, 439, 295, 300, 1491, 710, 15032, 6873, 767, 51205], "temperature": 0, "avg_logprob": -0.04963681253336244, "compression_ratio": 1.7107142857142856, "no_speech_prob": 2.1932388630935273e-12}, {"id": 3, "seek": 0, "start": 16.8, "end": 22.62, "text": " the way he announced it on the x platform i think he came back on it after a few years and look at", "tokens": [51205, 264, 636, 415, 7548, 309, 322, 264, 2031, 3663, 741, 519, 415, 1361, 646, 322, 309, 934, 257, 1326, 924, 293, 574, 412, 51496], "temperature": 0, "avg_logprob": -0.04963681253336244, "compression_ratio": 1.7107142857142856, "no_speech_prob": 2.1932388630935273e-12}, {"id": 4, "seek": 0, "start": 22.62, "end": 29.98, "text": " what he leads with a strong agentic and coding model at a very low price through our new meta", "tokens": [51496, 437, 415, 6689, 365, 257, 2068, 9461, 299, 293, 17720, 2316, 412, 257, 588, 2295, 3218, 807, 527, 777, 19616, 51864], "temperature": 0, "avg_logprob": -0.04963681253336244, "compression_ratio": 1.7107142857142856, "no_speech_prob": 2.1932388630935273e-12}, {"id": 5, "seek": 2998, "start": 29.98, "end": 37.78, "text": " model api a low price a paid api now think about this from a company that for years made free", "tokens": [50365, 2316, 1882, 72, 257, 2295, 3218, 257, 4835, 1882, 72, 586, 519, 466, 341, 490, 257, 2237, 300, 337, 924, 1027, 1737, 50755], "temperature": 0, "avg_logprob": -0.036588148138988974, "compression_ratio": 1.7043478260869565, "no_speech_prob": 1.2644861286520426e-12}, {"id": 6, "seek": 2998, "start": 37.78, "end": 44.84, "text": " and open source ai its entire identity so before i get into what spark can actually do i think it'll", "tokens": [50755, 293, 1269, 4009, 9783, 1080, 2302, 6575, 370, 949, 741, 483, 666, 437, 9908, 393, 767, 360, 741, 519, 309, 603, 51108], "temperature": 0, "avg_logprob": -0.036588148138988974, "compression_ratio": 1.7043478260869565, "no_speech_prob": 1.2644861286520426e-12}, {"id": 7, "seek": 2998, "start": 44.84, "end": 51.3, "text": " be interesting to understand what pushed meta to change the strategy like this so let's go back", "tokens": [51108, 312, 1880, 281, 1223, 437, 9152, 19616, 281, 1319, 264, 5206, 411, 341, 370, 718, 311, 352, 646, 51431], "temperature": 0, "avg_logprob": -0.036588148138988974, "compression_ratio": 1.7043478260869565, "no_speech_prob": 1.2644861286520426e-12}, {"id": 8, "seek": 2998, "start": 51.3, "end": 56.7, "text": " to history and rewind right because the backstory explains everything for years meta was the champion", "tokens": [51431, 281, 2503, 293, 41458, 558, 570, 264, 36899, 13948, 1203, 337, 924, 19616, 390, 264, 10971, 51701], "temperature": 0, "avg_logprob": -0.036588148138988974, "compression_ratio": 1.7043478260869565, "no_speech_prob": 1.2644861286520426e-12}, {"id": 9, "seek": 5670, "start": 56.7, "end": 64.82000000000001, "text": " of open source ai back in july 2024 zuck published an essay titled literally open source ai is the", "tokens": [50365, 295, 1269, 4009, 9783, 646, 294, 361, 3540, 45237, 710, 1134, 6572, 364, 16238, 19841, 3736, 1269, 4009, 9783, 307, 264, 50771], "temperature": 0, "avg_logprob": -0.06069908720074278, "compression_ratio": 1.553191489361702, "no_speech_prob": 2.4183556632945136e-12}, {"id": 10, "seek": 5670, "start": 64.82000000000001, "end": 70.88, "text": " path forward free downloadable models were meta's whole identity and he positioned the company as", "tokens": [50771, 3100, 2128, 1737, 5484, 712, 5245, 645, 19616, 311, 1379, 6575, 293, 415, 24889, 264, 2237, 382, 51074], "temperature": 0, "avg_logprob": -0.06069908720074278, "compression_ratio": 1.553191489361702, "no_speech_prob": 2.4183556632945136e-12}, {"id": 11, "seek": 5670, "start": 70.88, "end": 79.08, "text": " the open alternator to closed labs like open ai then it changed fast meta brought in scale ai's", "tokens": [51074, 264, 1269, 5400, 1639, 281, 5395, 20339, 411, 1269, 9783, 550, 309, 3105, 2370, 19616, 3038, 294, 4373, 9783, 311, 51484], "temperature": 0, "avg_logprob": -0.06069908720074278, "compression_ratio": 1.553191489361702, "no_speech_prob": 2.4183556632945136e-12}, {"id": 12, "seek": 7908, "start": 79.08, "end": 86.34, "text": " alexander van as their chief ai officer a 14 billion dollar deal they stood up a brand new super", "tokens": [50365, 257, 2021, 4483, 3161, 382, 641, 9588, 9783, 8456, 257, 3499, 5218, 7241, 2028, 436, 9371, 493, 257, 3360, 777, 1687, 50728], "temperature": 0, "avg_logprob": -0.08781017727322049, "compression_ratio": 1.6408163265306122, "no_speech_prob": 4.276492354682304e-12}, {"id": 13, "seek": 7908, "start": 86.34, "end": 93.38, "text": " intelligence lab and back in april shipped the first muke spark model which was closed no waits no", "tokens": [50728, 7599, 2715, 293, 646, 294, 10992, 388, 25312, 264, 700, 2992, 330, 9908, 2316, 597, 390, 5395, 572, 40597, 572, 51080], "temperature": 0, "avg_logprob": -0.08781017727322049, "compression_ratio": 1.6408163265306122, "no_speech_prob": 4.276492354682304e-12}, {"id": 14, "seek": 7908, "start": 93.38, "end": 99.72, "text": " download available that was a real break from open source for the first time right and meta's frontier", "tokens": [51080, 5484, 2435, 300, 390, 257, 957, 1821, 490, 1269, 4009, 337, 264, 700, 565, 558, 293, 19616, 311, 35853, 51397], "temperature": 0, "avg_logprob": -0.08781017727322049, "compression_ratio": 1.6408163265306122, "no_speech_prob": 4.276492354682304e-12}, {"id": 15, "seek": 7908, "start": 99.72, "end": 106.2, "text": " model were locked behind its own doors running inside its apps instead of out in the open and this week", "tokens": [51397, 2316, 645, 9376, 2261, 1080, 1065, 8077, 2614, 1854, 1080, 7733, 2602, 295, 484, 294, 264, 1269, 293, 341, 1243, 51721], "temperature": 0, "avg_logprob": -0.08781017727322049, "compression_ratio": 1.6408163265306122, "no_speech_prob": 4.276492354682304e-12}, {"id": 16, "seek": 10620, "start": 106.2, "end": 114.24000000000001, "text": " meta took the next step a big upgrade muse spark 1.1 and for the first time ever a public paid api", "tokens": [50365, 19616, 1890, 264, 958, 1823, 257, 955, 11484, 39138, 9908, 502, 13, 16, 293, 337, 264, 700, 565, 1562, 257, 1908, 4835, 1882, 72, 50767], "temperature": 0, "avg_logprob": -0.05878963374128245, "compression_ratio": 1.6527196652719665, "no_speech_prob": 4.064678281456846e-12}, {"id": 17, "seek": 10620, "start": 114.24000000000001, "end": 122.6, "text": " with pricing zuckerberg called very aggressive so meta didn't just close its best model it put a price", "tokens": [50767, 365, 17621, 710, 15032, 6873, 1219, 588, 10762, 370, 19616, 994, 380, 445, 1998, 1080, 1151, 2316, 309, 829, 257, 3218, 51185], "temperature": 0, "avg_logprob": -0.05878963374128245, "compression_ratio": 1.6527196652719665, "no_speech_prob": 4.064678281456846e-12}, {"id": 18, "seek": 10620, "start": 122.6, "end": 128.18, "text": " tag on it and open it up for anyone to build it meta didn't just undercut everyone on price", "tokens": [51185, 6162, 322, 309, 293, 1269, 309, 493, 337, 2878, 281, 1322, 309, 19616, 994, 380, 445, 833, 6672, 1518, 322, 3218, 51464], "temperature": 0, "avg_logprob": -0.05878963374128245, "compression_ratio": 1.6527196652719665, "no_speech_prob": 4.064678281456846e-12}, {"id": 19, "seek": 10620, "start": 128.18, "end": 135.56, "text": " it's about a quarter of what gpt and claude cost they also made mu spark drop straight into the tools", "tokens": [51464, 309, 311, 466, 257, 6555, 295, 437, 290, 662, 293, 3583, 2303, 2063, 436, 611, 1027, 2992, 9908, 3270, 2997, 666, 264, 3873, 51833], "temperature": 0, "avg_logprob": -0.05878963374128245, "compression_ratio": 1.6527196652719665, "no_speech_prob": 4.064678281456846e-12}, {"id": 20, "seek": 13556, "start": 135.56, "end": 142.4, "text": " developers already use open ai setup sure but also clawed code anthropic's own coding tool you pointed", "tokens": [50365, 8849, 1217, 764, 1269, 9783, 8657, 988, 457, 611, 32019, 292, 3089, 22727, 299, 311, 1065, 17720, 2290, 291, 10932, 50707], "temperature": 0, "avg_logprob": -0.07682501140393709, "compression_ratio": 1.6818181818181819, "no_speech_prob": 3.4088222695960457e-12}, {"id": 21, "seek": 13556, "start": 142.4, "end": 148.52, "text": " at meta's model change basically one line and now you're suddenly running on muse spark at a quarter of", "tokens": [50707, 412, 19616, 311, 2316, 1319, 1936, 472, 1622, 293, 586, 291, 434, 5800, 2614, 322, 39138, 9908, 412, 257, 6555, 295, 51013], "temperature": 0, "avg_logprob": -0.07682501140393709, "compression_ratio": 1.6818181818181819, "no_speech_prob": 3.4088222695960457e-12}, {"id": 22, "seek": 13556, "start": 148.52, "end": 155.96, "text": " the price meta built a side door out of open ai and anthropic and hung a discount sign on it this", "tokens": [51013, 264, 3218, 19616, 3094, 257, 1252, 2853, 484, 295, 1269, 9783, 293, 22727, 299, 293, 5753, 257, 11635, 1465, 322, 309, 341, 51385], "temperature": 0, "avg_logprob": -0.07682501140393709, "compression_ratio": 1.6818181818181819, "no_speech_prob": 3.4088222695960457e-12}, {"id": 23, "seek": 13556, "start": 155.96, "end": 162.1, "text": " isn't just a new model it's a direct play for their rivals customers now two things to keep honest one", "tokens": [51385, 1943, 380, 445, 257, 777, 2316, 309, 311, 257, 2047, 862, 337, 641, 33303, 4581, 586, 732, 721, 281, 1066, 3245, 472, 51692], "temperature": 0, "avg_logprob": -0.07682501140393709, "compression_ratio": 1.6818181818181819, "no_speech_prob": 3.4088222695960457e-12}, {"id": 24, "seek": 16210, "start": 162.1, "end": 167.85999999999999, "text": " llama isn't dead it's still open still downloadable what changes matters best models are closed now", "tokens": [50365, 23272, 1943, 380, 3116, 309, 311, 920, 1269, 920, 5484, 712, 437, 2962, 7001, 1151, 5245, 366, 5395, 586, 50653], "temperature": 0, "avg_logprob": -0.08068689409193101, "compression_ratio": 1.7533039647577093, "no_speech_prob": 3.685772607259219e-12}, {"id": 25, "seek": 16210, "start": 167.85999999999999, "end": 174.01999999999998, "text": " and two as wild as the flip feels it makes sense right matters spending north of a hundred billion", "tokens": [50653, 293, 732, 382, 4868, 382, 264, 7929, 3417, 309, 1669, 2020, 558, 7001, 6434, 6830, 295, 257, 3262, 5218, 50961], "temperature": 0, "avg_logprob": -0.08068689409193101, "compression_ratio": 1.7533039647577093, "no_speech_prob": 3.685772607259219e-12}, {"id": 26, "seek": 16210, "start": 174.01999999999998, "end": 179.29999999999998, "text": " dollars a year on ai you don't spend that and give your best model away and if you want a personal", "tokens": [50961, 3808, 257, 1064, 322, 9783, 291, 500, 380, 3496, 300, 293, 976, 428, 1151, 2316, 1314, 293, 498, 291, 528, 257, 2973, 51225], "temperature": 0, "avg_logprob": -0.08068689409193101, "compression_ratio": 1.7533039647577093, "no_speech_prob": 3.685772607259219e-12}, {"id": 27, "seek": 16210, "start": 179.29999999999998, "end": 185.74, "text": " agent in the hands of three billion people you want to own the model doing the work so what did they", "tokens": [51225, 9461, 294, 264, 2377, 295, 1045, 5218, 561, 291, 528, 281, 1065, 264, 2316, 884, 264, 589, 370, 437, 630, 436, 51547], "temperature": 0, "avg_logprob": -0.08068689409193101, "compression_ratio": 1.7533039647577093, "no_speech_prob": 3.685772607259219e-12}, {"id": 28, "seek": 18574, "start": 185.74, "end": 191.9, "text": " actually build and is it worth your time i started using it for the last couple of days and i also", "tokens": [50365, 767, 1322, 293, 307, 309, 3163, 428, 565, 741, 1409, 1228, 309, 337, 264, 1036, 1916, 295, 1708, 293, 741, 611, 50673], "temperature": 0, "avg_logprob": -0.05782061963041952, "compression_ratio": 1.7667844522968197, "no_speech_prob": 3.2526908683855327e-12}, {"id": 29, "seek": 18574, "start": 191.9, "end": 198.46, "text": " built a little app on meta's model i handed it a video of anything that you probably want to sell and", "tokens": [50673, 3094, 257, 707, 724, 322, 19616, 311, 2316, 741, 16013, 309, 257, 960, 295, 1340, 300, 291, 1391, 528, 281, 3607, 293, 51001], "temperature": 0, "avg_logprob": -0.05782061963041952, "compression_ratio": 1.7667844522968197, "no_speech_prob": 3.2526908683855327e-12}, {"id": 30, "seek": 18574, "start": 198.46, "end": 203.34, "text": " asked it to give me a full price ready to post listing on facebook's marketplace so that's one", "tokens": [51001, 2351, 309, 281, 976, 385, 257, 1577, 3218, 1919, 281, 2183, 22161, 322, 23372, 311, 19455, 370, 300, 311, 472, 51245], "temperature": 0, "avg_logprob": -0.05782061963041952, "compression_ratio": 1.7667844522968197, "no_speech_prob": 3.2526908683855327e-12}, {"id": 31, "seek": 18574, "start": 203.34, "end": 208.94, "text": " demo that we will see second i also ran it on clock course and tropic so that will be an interesting one", "tokens": [51245, 10723, 300, 321, 486, 536, 1150, 741, 611, 5872, 309, 322, 7830, 1164, 293, 9006, 299, 370, 300, 486, 312, 364, 1880, 472, 51525], "temperature": 0, "avg_logprob": -0.05782061963041952, "compression_ratio": 1.7667844522968197, "no_speech_prob": 3.2526908683855327e-12}, {"id": 32, "seek": 18574, "start": 208.94, "end": 214.06, "text": " and third i wanted to test the real multi-modality so i gave it a picture of the ingredients in the", "tokens": [51525, 293, 2636, 741, 1415, 281, 1500, 264, 957, 4825, 12, 8014, 1860, 370, 741, 2729, 309, 257, 3036, 295, 264, 6952, 294, 264, 51781], "temperature": 0, "avg_logprob": -0.05782061963041952, "compression_ratio": 1.7667844522968197, "no_speech_prob": 3.2526908683855327e-12}, {"id": 33, "seek": 21406, "start": 214.06, "end": 218.7, "text": " fridge and it was able to pinpoint the price tag on it right so i'll show you all of the fun parts as", "tokens": [50365, 13023, 293, 309, 390, 1075, 281, 40837, 264, 3218, 6162, 322, 309, 558, 370, 741, 603, 855, 291, 439, 295, 264, 1019, 3166, 382, 50597], "temperature": 0, "avg_logprob": -0.03628849131720407, "compression_ratio": 1.7184115523465704, "no_speech_prob": 2.305128744134466e-12}, {"id": 34, "seek": 21406, "start": 218.7, "end": 225.26, "text": " we go through but then interesting part as i mentioned earlier is meta shift to the paid", "tokens": [50597, 321, 352, 807, 457, 550, 1880, 644, 382, 741, 2835, 3071, 307, 19616, 5513, 281, 264, 4835, 50925], "temperature": 0, "avg_logprob": -0.03628849131720407, "compression_ratio": 1.7184115523465704, "no_speech_prob": 2.305128744134466e-12}, {"id": 35, "seek": 21406, "start": 225.26, "end": 230.54, "text": " strategy which is just keeping it open source all right before we dive deep into it a quick disclaimer", "tokens": [50925, 5206, 597, 307, 445, 5145, 309, 1269, 4009, 439, 558, 949, 321, 9192, 2452, 666, 309, 257, 1702, 40896, 51189], "temperature": 0, "avg_logprob": -0.03628849131720407, "compression_ratio": 1.7184115523465704, "no_speech_prob": 2.305128744134466e-12}, {"id": 36, "seek": 21406, "start": 230.54, "end": 235.74, "text": " all opinions are my own and do not belong to my employer all right with that let's get into it", "tokens": [51189, 439, 11819, 366, 452, 1065, 293, 360, 406, 5784, 281, 452, 16205, 439, 558, 365, 300, 718, 311, 483, 666, 309, 51449], "temperature": 0, "avg_logprob": -0.03628849131720407, "compression_ratio": 1.7184115523465704, "no_speech_prob": 2.305128744134466e-12}, {"id": 37, "seek": 21406, "start": 236.86, "end": 242.3, "text": " all right so one of the fastest ways to experience spark is to actually come to meta.ai", "tokens": [51505, 439, 558, 370, 472, 295, 264, 14573, 2098, 281, 1752, 9908, 307, 281, 767, 808, 281, 19616, 13, 1301, 51777], "temperature": 0, "avg_logprob": -0.03628849131720407, "compression_ratio": 1.7184115523465704, "no_speech_prob": 2.305128744134466e-12}, {"id": 38, "seek": 24230, "start": 242.3, "end": 247.34, "text": " and change the mode from instant to thinking mode so if you ask any question like for example here i'm", "tokens": [50365, 293, 1319, 264, 4391, 490, 9836, 281, 1953, 4391, 370, 498, 291, 1029, 604, 1168, 411, 337, 1365, 510, 741, 478, 50617], "temperature": 0, "avg_logprob": -0.038259683457096065, "compression_ratio": 1.797709923664122, "no_speech_prob": 3.354988379125623e-12}, {"id": 39, "seek": 24230, "start": 247.34, "end": 252.70000000000002, "text": " asking which particular meta model are you using you would see that it is going to confirm that it is", "tokens": [50617, 3365, 597, 1729, 19616, 2316, 366, 291, 1228, 291, 576, 536, 300, 309, 307, 516, 281, 9064, 300, 309, 307, 50885], "temperature": 0, "avg_logprob": -0.038259683457096065, "compression_ratio": 1.797709923664122, "no_speech_prob": 3.354988379125623e-12}, {"id": 40, "seek": 24230, "start": 252.70000000000002, "end": 259.18, "text": " using spark 1.1 so you just need to change the mode to thinking and you will get to leverage the spark", "tokens": [50885, 1228, 9908, 502, 13, 16, 370, 291, 445, 643, 281, 1319, 264, 4391, 281, 1953, 293, 291, 486, 483, 281, 13982, 264, 9908, 51209], "temperature": 0, "avg_logprob": -0.038259683457096065, "compression_ratio": 1.797709923664122, "no_speech_prob": 3.354988379125623e-12}, {"id": 41, "seek": 24230, "start": 259.18, "end": 265.18, "text": " 1.1 model right so it was launched literally a couple of days back okay but then from a developer", "tokens": [51209, 502, 13, 16, 2316, 558, 370, 309, 390, 8730, 3736, 257, 1916, 295, 1708, 646, 1392, 457, 550, 490, 257, 10754, 51509], "temperature": 0, "avg_logprob": -0.038259683457096065, "compression_ratio": 1.797709923664122, "no_speech_prob": 3.354988379125623e-12}, {"id": 42, "seek": 26518, "start": 265.18, "end": 272.46, "text": " perspective if you want to use it you need to go into dev.meta.ai so here i am in dev.meta.ai and i", "tokens": [50365, 4585, 498, 291, 528, 281, 764, 309, 291, 643, 281, 352, 666, 1905, 13, 5537, 64, 13, 1301, 370, 510, 741, 669, 294, 1905, 13, 5537, 64, 13, 1301, 293, 741, 50729], "temperature": 0, "avg_logprob": -0.05030175491615578, "compression_ratio": 1.8461538461538463, "no_speech_prob": 2.472059449504238e-12}, {"id": 43, "seek": 26518, "start": 272.46, "end": 279.1, "text": " was able to create an api key and you can already see detailed docs and how you're able to use this", "tokens": [50729, 390, 1075, 281, 1884, 364, 1882, 72, 2141, 293, 291, 393, 1217, 536, 9942, 45623, 293, 577, 291, 434, 1075, 281, 764, 341, 51061], "temperature": 0, "avg_logprob": -0.05030175491615578, "compression_ratio": 1.8461538461538463, "no_speech_prob": 2.472059449504238e-12}, {"id": 44, "seek": 26518, "start": 279.1, "end": 284.22, "text": " in plot code and these are all the details that they have provided codecs then if you want to just call", "tokens": [51061, 294, 7542, 3089, 293, 613, 366, 439, 264, 4365, 300, 436, 362, 5649, 3089, 14368, 550, 498, 291, 528, 281, 445, 818, 51317], "temperature": 0, "avg_logprob": -0.05030175491615578, "compression_ratio": 1.8461538461538463, "no_speech_prob": 2.472059449504238e-12}, {"id": 45, "seek": 26518, "start": 284.22, "end": 289.26, "text": " it via python as well as curl right these are some of the details that have been given so what you could", "tokens": [51317, 309, 5766, 38797, 382, 731, 382, 22591, 558, 613, 366, 512, 295, 264, 4365, 300, 362, 668, 2212, 370, 437, 291, 727, 51569], "temperature": 0, "avg_logprob": -0.05030175491615578, "compression_ratio": 1.8461538461538463, "no_speech_prob": 2.472059449504238e-12}, {"id": 46, "seek": 28926, "start": 289.26, "end": 294.38, "text": " do is you can create an api key so what i did was as i mentioned earlier i'm going to be doing three", "tokens": [50365, 360, 307, 291, 393, 1884, 364, 1882, 72, 2141, 370, 437, 741, 630, 390, 382, 741, 2835, 3071, 741, 478, 516, 281, 312, 884, 1045, 50621], "temperature": 0, "avg_logprob": -0.04005227770124163, "compression_ratio": 1.895910780669145, "no_speech_prob": 2.869707292976753e-12}, {"id": 47, "seek": 28926, "start": 294.38, "end": 300.86, "text": " different demos so the first demo here is think of it like a facebook marketplace listing generator so", "tokens": [50621, 819, 33788, 370, 264, 700, 10723, 510, 307, 519, 295, 309, 411, 257, 23372, 19455, 22161, 19265, 370, 50945], "temperature": 0, "avg_logprob": -0.04005227770124163, "compression_ratio": 1.895910780669145, "no_speech_prob": 2.869707292976753e-12}, {"id": 48, "seek": 28926, "start": 300.86, "end": 306.3, "text": " here i would be using muse park so what i'm going to do here is upload a video here so you can see the", "tokens": [50945, 510, 741, 576, 312, 1228, 39138, 3884, 370, 437, 741, 478, 516, 281, 360, 510, 307, 6580, 257, 960, 510, 370, 291, 393, 536, 264, 51217], "temperature": 0, "avg_logprob": -0.04005227770124163, "compression_ratio": 1.895910780669145, "no_speech_prob": 2.869707292976753e-12}, {"id": 49, "seek": 28926, "start": 306.3, "end": 313.02, "text": " video very clearly this is a video of a bike of a kid where i've just taken like a very short nine", "tokens": [51217, 960, 588, 4448, 341, 307, 257, 960, 295, 257, 5656, 295, 257, 1636, 689, 741, 600, 445, 2726, 411, 257, 588, 2099, 4949, 51553], "temperature": 0, "avg_logprob": -0.04005227770124163, "compression_ratio": 1.895910780669145, "no_speech_prob": 2.869707292976753e-12}, {"id": 50, "seek": 28926, "start": 313.02, "end": 318.46, "text": " seconds i just wanted to make it a little bit tough and i'm going to ask it to generate listing right so", "tokens": [51553, 3949, 741, 445, 1415, 281, 652, 309, 257, 707, 857, 4930, 293, 741, 478, 516, 281, 1029, 309, 281, 8460, 22161, 558, 370, 51825], "temperature": 0, "avg_logprob": -0.04005227770124163, "compression_ratio": 1.895910780669145, "no_speech_prob": 2.869707292976753e-12}, {"id": 51, "seek": 31846, "start": 318.46, "end": 322.7, "text": " there are multiple things which are happening here right so obviously it is calling the muse", "tokens": [50365, 456, 366, 3866, 721, 597, 366, 2737, 510, 558, 370, 2745, 309, 307, 5141, 264, 39138, 50577], "temperature": 0, "avg_logprob": -0.05300295030748522, "compression_ratio": 1.8432835820895523, "no_speech_prob": 3.079581077994331e-12}, {"id": 52, "seek": 31846, "start": 322.7, "end": 328.38, "text": " spark 1.1 model so the first thing what's happening here is it is going to be identifying the item", "tokens": [50577, 9908, 502, 13, 16, 2316, 370, 264, 700, 551, 437, 311, 2737, 510, 307, 309, 307, 516, 281, 312, 16696, 264, 3174, 50861], "temperature": 0, "avg_logprob": -0.05300295030748522, "compression_ratio": 1.8432835820895523, "no_speech_prob": 3.079581077994331e-12}, {"id": 53, "seek": 31846, "start": 328.38, "end": 334.21999999999997, "text": " so this is the response back from the first step so it has correctly identified that this is a global", "tokens": [50861, 370, 341, 307, 264, 4134, 646, 490, 264, 700, 1823, 370, 309, 575, 8944, 9234, 300, 341, 307, 257, 4338, 51153], "temperature": 0, "avg_logprob": -0.05300295030748522, "compression_ratio": 1.8432835820895523, "no_speech_prob": 3.079581077994331e-12}, {"id": 54, "seek": 31846, "start": 334.21999999999997, "end": 339.65999999999997, "text": " primo pink three wheel kit scooter and obviously it is used so it has understood that as well so very", "tokens": [51153, 38671, 7022, 1045, 5589, 8260, 30441, 293, 2745, 309, 307, 1143, 370, 309, 575, 7320, 300, 382, 731, 370, 588, 51425], "temperature": 0, "avg_logprob": -0.05300295030748522, "compression_ratio": 1.8432835820895523, "no_speech_prob": 3.079581077994331e-12}, {"id": 55, "seek": 31846, "start": 339.65999999999997, "end": 345.34, "text": " good job done very quickly you can see the amount of time it took was very short then the agent is", "tokens": [51425, 665, 1691, 1096, 588, 2661, 291, 393, 536, 264, 2372, 295, 565, 309, 1890, 390, 588, 2099, 550, 264, 9461, 307, 51709], "temperature": 0, "avg_logprob": -0.05300295030748522, "compression_ratio": 1.8432835820895523, "no_speech_prob": 3.079581077994331e-12}, {"id": 56, "seek": 34534, "start": 345.34, "end": 351.26, "text": " going to now do a pricing research so it's going to look into some other prices so that it can give", "tokens": [50365, 516, 281, 586, 360, 257, 17621, 2132, 370, 309, 311, 516, 281, 574, 666, 512, 661, 7901, 370, 300, 309, 393, 976, 50661], "temperature": 0, "avg_logprob": -0.03681392836989018, "compression_ratio": 2.0121951219512195, "no_speech_prob": 2.7685371356556132e-12}, {"id": 57, "seek": 34534, "start": 351.26, "end": 357.34, "text": " us some comparison pricing right once you have that idea of the comparison pricing then it will", "tokens": [50661, 505, 512, 9660, 17621, 558, 1564, 291, 362, 300, 1558, 295, 264, 9660, 17621, 550, 309, 486, 50965], "temperature": 0, "avg_logprob": -0.03681392836989018, "compression_ratio": 2.0121951219512195, "no_speech_prob": 2.7685371356556132e-12}, {"id": 58, "seek": 34534, "start": 357.34, "end": 362.85999999999996, "text": " consolidate all of that and create the listing so you can see that i'll search current resale listing", "tokens": [50965, 49521, 439, 295, 300, 293, 1884, 264, 22161, 370, 291, 393, 536, 300, 741, 603, 3164, 2190, 725, 1220, 22161, 51241], "temperature": 0, "avg_logprob": -0.03681392836989018, "compression_ratio": 2.0121951219512195, "no_speech_prob": 2.7685371356556132e-12}, {"id": 59, "seek": 34534, "start": 362.85999999999996, "end": 368.62, "text": " for your global this in the us market it is around this and you can see all the pricing over here", "tokens": [51241, 337, 428, 4338, 341, 294, 264, 505, 2142, 309, 307, 926, 341, 293, 291, 393, 536, 439, 264, 17621, 670, 510, 51529], "temperature": 0, "avg_logprob": -0.03681392836989018, "compression_ratio": 2.0121951219512195, "no_speech_prob": 2.7685371356556132e-12}, {"id": 60, "seek": 34534, "start": 368.62, "end": 373.9, "text": " in uk it is something of this sort right in canada it is this right and because this is coming from", "tokens": [51529, 294, 26769, 309, 307, 746, 295, 341, 1333, 558, 294, 393, 1538, 309, 307, 341, 558, 293, 570, 341, 307, 1348, 490, 51793], "temperature": 0, "avg_logprob": -0.03681392836989018, "compression_ratio": 2.0121951219512195, "no_speech_prob": 2.7685371356556132e-12}, {"id": 61, "seek": 37390, "start": 373.9, "end": 379.58, "text": " meta and facebook so and this is marketplace api so you will be able to actually get the right", "tokens": [50365, 19616, 293, 23372, 370, 293, 341, 307, 19455, 1882, 72, 370, 291, 486, 312, 1075, 281, 767, 483, 264, 558, 50649], "temperature": 0, "avg_logprob": -0.06013183256166171, "compression_ratio": 1.8407407407407408, "no_speech_prob": 2.836274401105121e-12}, {"id": 62, "seek": 37390, "start": 379.58, "end": 384.21999999999997, "text": " because they already have the data so now it has already created the listing so you can clearly see", "tokens": [50649, 570, 436, 1217, 362, 264, 1412, 370, 586, 309, 575, 1217, 2942, 264, 22161, 370, 291, 393, 4448, 536, 50881], "temperature": 0, "avg_logprob": -0.06013183256166171, "compression_ratio": 1.8407407407407408, "no_speech_prob": 2.836274401105121e-12}, {"id": 63, "seek": 37390, "start": 384.21999999999997, "end": 390.29999999999995, "text": " that global primo pink three wheel kit scooter hot pink and black it also identified this the best for", "tokens": [50881, 300, 4338, 38671, 7022, 1045, 5589, 8260, 30441, 2368, 7022, 293, 2211, 309, 611, 9234, 341, 264, 1151, 337, 51185], "temperature": 0, "avg_logprob": -0.06013183256166171, "compression_ratio": 1.8407407407407408, "no_speech_prob": 2.836274401105121e-12}, {"id": 64, "seek": 37390, "start": 390.29999999999995, "end": 395.9, "text": " scooter for toddlers and kids this is condition is very good the retails for this but then here we", "tokens": [51185, 30441, 337, 33268, 11977, 293, 2301, 341, 307, 4188, 307, 588, 665, 264, 1533, 6227, 337, 341, 457, 550, 510, 321, 51465], "temperature": 0, "avg_logprob": -0.06013183256166171, "compression_ratio": 1.8407407407407408, "no_speech_prob": 2.836274401105121e-12}, {"id": 65, "seek": 37390, "start": 395.9, "end": 401.02, "text": " are charging it at this particular price right so that's what it was able to do and you can see that", "tokens": [51465, 366, 11379, 309, 412, 341, 1729, 3218, 558, 370, 300, 311, 437, 309, 390, 1075, 281, 360, 293, 291, 393, 536, 300, 51721], "temperature": 0, "avg_logprob": -0.06013183256166171, "compression_ratio": 1.8407407407407408, "no_speech_prob": 2.836274401105121e-12}, {"id": 66, "seek": 40102, "start": 401.02, "end": 406.21999999999997, "text": " it did a pretty good job and you were able to then copy this and just take it and paste it in in", "tokens": [50365, 309, 630, 257, 1238, 665, 1691, 293, 291, 645, 1075, 281, 550, 5055, 341, 293, 445, 747, 309, 293, 9163, 309, 294, 294, 50625], "temperature": 0, "avg_logprob": -0.059982201148723734, "compression_ratio": 1.8327402135231317, "no_speech_prob": 3.2022370866080507e-12}, {"id": 67, "seek": 40102, "start": 406.21999999999997, "end": 412.85999999999996, "text": " marketplace right so the reason i wanted to do this was to show you how you're able to create something", "tokens": [50625, 19455, 558, 370, 264, 1778, 741, 1415, 281, 360, 341, 390, 281, 855, 291, 577, 291, 434, 1075, 281, 1884, 746, 50957], "temperature": 0, "avg_logprob": -0.059982201148723734, "compression_ratio": 1.8327402135231317, "no_speech_prob": 3.2022370866080507e-12}, {"id": 68, "seek": 40102, "start": 412.85999999999996, "end": 418.14, "text": " like this very quickly using new spark and it really demonstrates an agentic behavior understanding of", "tokens": [50957, 411, 341, 588, 2661, 1228, 777, 9908, 293, 309, 534, 31034, 364, 9461, 299, 5223, 3701, 295, 51221], "temperature": 0, "avg_logprob": -0.059982201148723734, "compression_ratio": 1.8327402135231317, "no_speech_prob": 3.2022370866080507e-12}, {"id": 69, "seek": 40102, "start": 418.14, "end": 423.97999999999996, "text": " a multimodal input in this case video and also doing a quick search and then not only just limited to the", "tokens": [51221, 257, 32972, 378, 304, 4846, 294, 341, 1389, 960, 293, 611, 884, 257, 1702, 3164, 293, 550, 406, 787, 445, 5567, 281, 264, 51513], "temperature": 0, "avg_logprob": -0.059982201148723734, "compression_ratio": 1.8327402135231317, "no_speech_prob": 3.2022370866080507e-12}, {"id": 70, "seek": 40102, "start": 423.97999999999996, "end": 429.34, "text": " us but also search across the board and then providing you like a competitive pricing right so i was very", "tokens": [51513, 505, 457, 611, 3164, 2108, 264, 3150, 293, 550, 6530, 291, 411, 257, 10043, 17621, 558, 370, 741, 390, 588, 51781], "temperature": 0, "avg_logprob": -0.059982201148723734, "compression_ratio": 1.8327402135231317, "no_speech_prob": 3.2022370866080507e-12}, {"id": 71, "seek": 42934, "start": 429.34, "end": 434.78, "text": " impressed with what i saw okay so that's that's the first demo i hope you enjoyed it now what i want", "tokens": [50365, 11679, 365, 437, 741, 1866, 1392, 370, 300, 311, 300, 311, 264, 700, 10723, 741, 1454, 291, 4626, 309, 586, 437, 741, 528, 50637], "temperature": 0, "avg_logprob": -0.07025671888280798, "compression_ratio": 1.7854077253218885, "no_speech_prob": 2.7064162543000148e-12}, {"id": 72, "seek": 42934, "start": 434.78, "end": 440.94, "text": " to do here is i actually want to show you how you are also able to use it directly in claw code so for", "tokens": [50637, 281, 360, 510, 307, 741, 767, 528, 281, 855, 291, 577, 291, 366, 611, 1075, 281, 764, 309, 3838, 294, 32019, 3089, 370, 337, 50945], "temperature": 0, "avg_logprob": -0.07025671888280798, "compression_ratio": 1.7854077253218885, "no_speech_prob": 2.7064162543000148e-12}, {"id": 73, "seek": 42934, "start": 440.94, "end": 449.02, "text": " that let's just open clawed right so in this case i've already configured clods connector so if i show you", "tokens": [50945, 300, 718, 311, 445, 1269, 32019, 292, 558, 370, 294, 341, 1389, 741, 600, 1217, 30538, 596, 19768, 19127, 370, 498, 741, 855, 291, 51349], "temperature": 0, "avg_logprob": -0.07025671888280798, "compression_ratio": 1.7854077253218885, "no_speech_prob": 2.7064162543000148e-12}, {"id": 74, "seek": 42934, "start": 449.02, "end": 456.14, "text": " this you can see that here i have got the new spark 1.1 agent here right so the way i was able to do this", "tokens": [51349, 341, 291, 393, 536, 300, 510, 741, 362, 658, 264, 777, 9908, 502, 13, 16, 9461, 510, 558, 370, 264, 636, 741, 390, 1075, 281, 360, 341, 51705], "temperature": 0, "avg_logprob": -0.07025671888280798, "compression_ratio": 1.7854077253218885, "no_speech_prob": 2.7064162543000148e-12}, {"id": 75, "seek": 45614, "start": 456.14, "end": 461.9, "text": " was i basically followed this specific instruction here i provided the api key which i already showed", "tokens": [50365, 390, 741, 1936, 6263, 341, 2685, 10951, 510, 741, 5649, 264, 1882, 72, 2141, 597, 741, 1217, 4712, 50653], "temperature": 0, "avg_logprob": -0.0385971170790652, "compression_ratio": 1.7816593886462881, "no_speech_prob": 2.9840585297896682e-12}, {"id": 76, "seek": 45614, "start": 461.9, "end": 468.46, "text": " you and i ran this in powershell first right so before actually running clawed i basically ran this", "tokens": [50653, 291, 293, 741, 5872, 341, 294, 8674, 21288, 700, 558, 370, 949, 767, 2614, 32019, 292, 741, 1936, 5872, 341, 50981], "temperature": 0, "avg_logprob": -0.0385971170790652, "compression_ratio": 1.7816593886462881, "no_speech_prob": 2.9840585297896682e-12}, {"id": 77, "seek": 45614, "start": 468.46, "end": 475.09999999999997, "text": " right so once i have this now clawed is being forced to use this particular model which is new spark 1.1", "tokens": [50981, 558, 370, 1564, 741, 362, 341, 586, 32019, 292, 307, 885, 7579, 281, 764, 341, 1729, 2316, 597, 307, 777, 9908, 502, 13, 16, 51313], "temperature": 0, "avg_logprob": -0.0385971170790652, "compression_ratio": 1.7816593886462881, "no_speech_prob": 2.9840585297896682e-12}, {"id": 78, "seek": 45614, "start": 475.09999999999997, "end": 480.86, "text": " right so you are welcome to try this and see what kind of results you're getting all right so for the", "tokens": [51313, 558, 370, 291, 366, 2928, 281, 853, 341, 293, 536, 437, 733, 295, 3542, 291, 434, 1242, 439, 558, 370, 337, 264, 51601], "temperature": 0, "avg_logprob": -0.0385971170790652, "compression_ratio": 1.7816593886462881, "no_speech_prob": 2.9840585297896682e-12}, {"id": 79, "seek": 48086, "start": 480.86, "end": 486.22, "text": " third demo i decided to actually use one of meta's cookbooks which they have given and they have really", "tokens": [50365, 2636, 10723, 741, 3047, 281, 767, 764, 472, 295, 19616, 311, 2543, 15170, 597, 436, 362, 2212, 293, 436, 362, 534, 50633], "temperature": 0, "avg_logprob": -0.0430345954475822, "compression_ratio": 1.755458515283843, "no_speech_prob": 3.1150338385133036e-12}, {"id": 80, "seek": 48086, "start": 486.22, "end": 492.3, "text": " done a great job and provided 10 actually 13 different use cases so here in this one i actually", "tokens": [50633, 1096, 257, 869, 1691, 293, 5649, 1266, 767, 3705, 819, 764, 3331, 370, 510, 294, 341, 472, 741, 767, 50937], "temperature": 0, "avg_logprob": -0.0430345954475822, "compression_ratio": 1.755458515283843, "no_speech_prob": 3.1150338385133036e-12}, {"id": 81, "seek": 48086, "start": 492.3, "end": 499.02000000000004, "text": " decided to use this perception grounding right so the use case here is you have your fridge filled with", "tokens": [50937, 3047, 281, 764, 341, 12860, 46727, 558, 370, 264, 764, 1389, 510, 307, 291, 362, 428, 13023, 6412, 365, 51273], "temperature": 0, "avg_logprob": -0.0430345954475822, "compression_ratio": 1.755458515283843, "no_speech_prob": 3.1150338385133036e-12}, {"id": 82, "seek": 48086, "start": 499.02000000000004, "end": 505.90000000000003, "text": " some food objects and can meta's multimodal model be able to get and identify each one of the food", "tokens": [51273, 512, 1755, 6565, 293, 393, 19616, 311, 32972, 378, 304, 2316, 312, 1075, 281, 483, 293, 5876, 1184, 472, 295, 264, 1755, 51617], "temperature": 0, "avg_logprob": -0.0430345954475822, "compression_ratio": 1.755458515283843, "no_speech_prob": 3.1150338385133036e-12}, {"id": 83, "seek": 50590, "start": 505.9, "end": 512.54, "text": " objects and provide some sort of a score right so if i go in detail like this is the original image", "tokens": [50365, 6565, 293, 2893, 512, 1333, 295, 257, 6175, 558, 370, 498, 741, 352, 294, 2607, 411, 341, 307, 264, 3380, 3256, 50697], "temperature": 0, "avg_logprob": -0.046039994839018425, "compression_ratio": 1.8656716417910448, "no_speech_prob": 3.542384267862797e-12}, {"id": 84, "seek": 50590, "start": 512.54, "end": 517.5799999999999, "text": " you can see all the different food items over here and once you basically run this particular program", "tokens": [50697, 291, 393, 536, 439, 264, 819, 1755, 4754, 670, 510, 293, 1564, 291, 1936, 1190, 341, 1729, 1461, 50949], "temperature": 0, "avg_logprob": -0.046039994839018425, "compression_ratio": 1.8656716417910448, "no_speech_prob": 3.542384267862797e-12}, {"id": 85, "seek": 50590, "start": 517.5799999999999, "end": 524.54, "text": " and provide your api key it should be able to identify each one of these items and provide the", "tokens": [50949, 293, 2893, 428, 1882, 72, 2141, 309, 820, 312, 1075, 281, 5876, 1184, 472, 295, 613, 4754, 293, 2893, 264, 51297], "temperature": 0, "avg_logprob": -0.046039994839018425, "compression_ratio": 1.8656716417910448, "no_speech_prob": 3.542384267862797e-12}, {"id": 86, "seek": 50590, "start": 524.54, "end": 529.74, "text": " score right so what i did was i ran this particular prompt right i'm a pescetarian with high cholesterol", "tokens": [51297, 6175, 558, 370, 437, 741, 630, 390, 741, 5872, 341, 1729, 12391, 558, 741, 478, 257, 9262, 66, 302, 10652, 365, 1090, 24716, 51557], "temperature": 0, "avg_logprob": -0.046039994839018425, "compression_ratio": 1.8656716417910448, "no_speech_prob": 3.542384267862797e-12}, {"id": 87, "seek": 50590, "start": 529.74, "end": 535.74, "text": " put green dots on recommended food and now that it has run this particular output once i give this", "tokens": [51557, 829, 3092, 15026, 322, 9628, 1755, 293, 586, 300, 309, 575, 1190, 341, 1729, 5598, 1564, 741, 976, 341, 51857], "temperature": 0, "avg_logprob": -0.046039994839018425, "compression_ratio": 1.8656716417910448, "no_speech_prob": 3.542384267862797e-12}, {"id": 88, "seek": 53574, "start": 535.74, "end": 542.78, "text": " particular command i will be able to see the output right you can see it is now generating the html overlay", "tokens": [50365, 1729, 5622, 741, 486, 312, 1075, 281, 536, 264, 5598, 558, 291, 393, 536, 309, 307, 586, 17746, 264, 276, 83, 15480, 31741, 50717], "temperature": 0, "avg_logprob": -0.022687355677286785, "compression_ratio": 1.9855769230769231, "no_speech_prob": 3.9502095171284335e-12}, {"id": 89, "seek": 53574, "start": 542.78, "end": 548.3, "text": " so that it will be able to identify that right so i want to also show you the output of what it", "tokens": [50717, 370, 300, 309, 486, 312, 1075, 281, 5876, 300, 558, 370, 741, 528, 281, 611, 855, 291, 264, 5598, 295, 437, 309, 50993], "temperature": 0, "avg_logprob": -0.022687355677286785, "compression_ratio": 1.9855769230769231, "no_speech_prob": 3.9502095171284335e-12}, {"id": 90, "seek": 53574, "start": 548.3, "end": 554.78, "text": " produces so again just for the reference this is how the original picture looks like right so if you look", "tokens": [50993, 14725, 370, 797, 445, 337, 264, 6408, 341, 307, 577, 264, 3380, 3036, 1542, 411, 558, 370, 498, 291, 574, 51317], "temperature": 0, "avg_logprob": -0.022687355677286785, "compression_ratio": 1.9855769230769231, "no_speech_prob": 3.9502095171284335e-12}, {"id": 91, "seek": 53574, "start": 554.78, "end": 560.46, "text": " at this is how the picture looks like now what we will be able to generate is something like this which", "tokens": [51317, 412, 341, 307, 577, 264, 3036, 1542, 411, 586, 437, 321, 486, 312, 1075, 281, 8460, 307, 746, 411, 341, 597, 51601], "temperature": 0, "avg_logprob": -0.022687355677286785, "compression_ratio": 1.9855769230769231, "no_speech_prob": 3.9502095171284335e-12}, {"id": 92, "seek": 56046, "start": 560.46, "end": 566.22, "text": " is after after it has generated the output right so pescetarian plus high cholesterol fridge guide", "tokens": [50365, 307, 934, 934, 309, 575, 10833, 264, 5598, 558, 370, 9262, 66, 302, 10652, 1804, 1090, 24716, 13023, 5934, 50653], "temperature": 0, "avg_logprob": -0.05256464193155477, "compression_ratio": 1.7991266375545851, "no_speech_prob": 3.447967822714504e-12}, {"id": 93, "seek": 56046, "start": 566.22, "end": 571.5, "text": " recommended and not recommended and you can see the scores pretty much well done so this is the output", "tokens": [50653, 9628, 293, 406, 9628, 293, 291, 393, 536, 264, 13444, 1238, 709, 731, 1096, 370, 341, 307, 264, 5598, 50917], "temperature": 0, "avg_logprob": -0.05256464193155477, "compression_ratio": 1.7991266375545851, "no_speech_prob": 3.447967822714504e-12}, {"id": 94, "seek": 56046, "start": 571.5, "end": 577.02, "text": " and again thought like this was amazing because you can see orange juice we all think that it is great but", "tokens": [50917, 293, 797, 1194, 411, 341, 390, 2243, 570, 291, 393, 536, 7671, 8544, 321, 439, 519, 300, 309, 307, 869, 457, 51193], "temperature": 0, "avg_logprob": -0.05256464193155477, "compression_ratio": 1.7991266375545851, "no_speech_prob": 3.447967822714504e-12}, {"id": 95, "seek": 56046, "start": 577.02, "end": 583.4200000000001, "text": " for some reason it is giving not a great score so let's see if i eat something which is not recommended", "tokens": [51193, 337, 512, 1778, 309, 307, 2902, 406, 257, 869, 6175, 370, 718, 311, 536, 498, 741, 1862, 746, 597, 307, 406, 9628, 51513], "temperature": 0, "avg_logprob": -0.05256464193155477, "compression_ratio": 1.7991266375545851, "no_speech_prob": 3.447967822714504e-12}, {"id": 96, "seek": 58342, "start": 583.42, "end": 588.3, "text": " so cheese pack is not recommended yellow cheese is not recommended whereas this butter is definitely", "tokens": [50365, 370, 5399, 2844, 307, 406, 9628, 5566, 5399, 307, 406, 9628, 9735, 341, 5517, 307, 2138, 50609], "temperature": 0, "avg_logprob": -0.038472747802734374, "compression_ratio": 1.89010989010989, "no_speech_prob": 2.7170104274082396e-12}, {"id": 97, "seek": 58342, "start": 588.3, "end": 593.42, "text": " not recommended so pretty cool right so you are able to use this out of the box and able to get this", "tokens": [50609, 406, 9628, 370, 1238, 1627, 558, 370, 291, 366, 1075, 281, 764, 341, 484, 295, 264, 2424, 293, 1075, 281, 483, 341, 50865], "temperature": 0, "avg_logprob": -0.038472747802734374, "compression_ratio": 1.89010989010989, "no_speech_prob": 2.7170104274082396e-12}, {"id": 98, "seek": 58342, "start": 593.42, "end": 599.9, "text": " label and it's fast it's cheaper as well so this is what i wanted to cover the main idea is a make you", "tokens": [50865, 7645, 293, 309, 311, 2370, 309, 311, 12284, 382, 731, 370, 341, 307, 437, 741, 1415, 281, 2060, 264, 2135, 1558, 307, 257, 652, 291, 51189], "temperature": 0, "avg_logprob": -0.038472747802734374, "compression_ratio": 1.89010989010989, "no_speech_prob": 2.7170104274082396e-12}, {"id": 99, "seek": 58342, "start": 599.9, "end": 607.26, "text": " aware of this is a brand new agentic model out there so definitely give it a try you can see there like", "tokens": [51189, 3650, 295, 341, 307, 257, 3360, 777, 9461, 299, 2316, 484, 456, 370, 2138, 976, 309, 257, 853, 291, 393, 536, 456, 411, 51557], "temperature": 0, "avg_logprob": -0.038472747802734374, "compression_ratio": 1.89010989010989, "no_speech_prob": 2.7170104274082396e-12}, {"id": 100, "seek": 58342, "start": 607.26, "end": 612.38, "text": " this is a good playground and a dashboard so i've been playing with it it provides like the usage and stuff", "tokens": [51557, 341, 307, 257, 665, 24646, 293, 257, 18342, 370, 741, 600, 668, 2433, 365, 309, 309, 6417, 411, 264, 14924, 293, 1507, 51813], "temperature": 0, "avg_logprob": -0.038472747802734374, "compression_ratio": 1.89010989010989, "no_speech_prob": 2.7170104274082396e-12}, {"id": 101, "seek": 61238, "start": 612.38, "end": 618.54, "text": " like that very well etc all of those things and then they have also given like 20 free so so far", "tokens": [50365, 411, 300, 588, 731, 5183, 439, 295, 729, 721, 293, 550, 436, 362, 611, 2212, 411, 945, 1737, 370, 370, 1400, 50673], "temperature": 0, "avg_logprob": -0.04647009372711182, "compression_ratio": 1.8078291814946619, "no_speech_prob": 2.868749725618014e-12}, {"id": 102, "seek": 61238, "start": 618.54, "end": 623.18, "text": " i've ran it a few times and i only spent less than a dollar and there's another way for you to try which", "tokens": [50673, 741, 600, 5872, 309, 257, 1326, 1413, 293, 741, 787, 4418, 1570, 813, 257, 7241, 293, 456, 311, 1071, 636, 337, 291, 281, 853, 597, 50905], "temperature": 0, "avg_logprob": -0.04647009372711182, "compression_ratio": 1.8078291814946619, "no_speech_prob": 2.868749725618014e-12}, {"id": 103, "seek": 61238, "start": 623.18, "end": 627.74, "text": " is playground so you can upload an image or ask certain questions you can also change some of the", "tokens": [50905, 307, 24646, 370, 291, 393, 6580, 364, 3256, 420, 1029, 1629, 1651, 291, 393, 611, 1319, 512, 295, 264, 51133], "temperature": 0, "avg_logprob": -0.04647009372711182, "compression_ratio": 1.8078291814946619, "no_speech_prob": 2.868749725618014e-12}, {"id": 104, "seek": 61238, "start": 627.74, "end": 632.22, "text": " settings over here and then there are some advanced settings as well right you can add some json schema", "tokens": [51133, 6257, 670, 510, 293, 550, 456, 366, 512, 7339, 6257, 382, 731, 558, 291, 393, 909, 512, 361, 3015, 34078, 51357], "temperature": 0, "avg_logprob": -0.04647009372711182, "compression_ratio": 1.8078291814946619, "no_speech_prob": 2.868749725618014e-12}, {"id": 105, "seek": 61238, "start": 632.22, "end": 637.58, "text": " and stuff like that so what i would recommend is give it a shot also try it in a cop in combination with", "tokens": [51357, 293, 1507, 411, 300, 370, 437, 741, 576, 2748, 307, 976, 309, 257, 3347, 611, 853, 309, 294, 257, 2971, 294, 6562, 365, 51625], "temperature": 0, "avg_logprob": -0.04647009372711182, "compression_ratio": 1.8078291814946619, "no_speech_prob": 2.868749725618014e-12}, {"id": 106, "seek": 63758, "start": 637.58, "end": 643.58, "text": " clock code the app that i built i asked anti-gravity to actually build the app but leveraging the spark", "tokens": [50365, 7830, 3089, 264, 724, 300, 741, 3094, 741, 2351, 6061, 12, 36418, 507, 281, 767, 1322, 264, 724, 457, 32666, 264, 9908, 50665], "temperature": 0, "avg_logprob": -0.05112073295994809, "compression_ratio": 1.7758007117437722, "no_speech_prob": 2.454627213294147e-12}, {"id": 107, "seek": 63758, "start": 643.58, "end": 648.38, "text": " api you could do like all of these types of combination where you use your id and build an", "tokens": [50665, 1882, 72, 291, 727, 360, 411, 439, 295, 613, 3467, 295, 6562, 689, 291, 764, 428, 4496, 293, 1322, 364, 50905], "temperature": 0, "avg_logprob": -0.05112073295994809, "compression_ratio": 1.7758007117437722, "no_speech_prob": 2.454627213294147e-12}, {"id": 108, "seek": 63758, "start": 648.38, "end": 653.58, "text": " app like this and see for yourself what you feel as the performance right and obviously on the benchmarks", "tokens": [50905, 724, 411, 341, 293, 536, 337, 1803, 437, 291, 841, 382, 264, 3389, 558, 293, 2745, 322, 264, 43751, 51165], "temperature": 0, "avg_logprob": -0.05112073295994809, "compression_ratio": 1.7758007117437722, "no_speech_prob": 2.454627213294147e-12}, {"id": 109, "seek": 63758, "start": 653.58, "end": 659.1800000000001, "text": " they have talked about the benchmarks over here they've compared themselves against gemini 3.1 4.8", "tokens": [51165, 436, 362, 2825, 466, 264, 43751, 670, 510, 436, 600, 5347, 2969, 1970, 7173, 3812, 805, 13, 16, 1017, 13, 23, 51445], "temperature": 0, "avg_logprob": -0.05112073295994809, "compression_ratio": 1.7758007117437722, "no_speech_prob": 2.454627213294147e-12}, {"id": 110, "seek": 63758, "start": 659.1800000000001, "end": 664.7800000000001, "text": " these are here for your reading and i will share this as well of course does all different types of", "tokens": [51445, 613, 366, 510, 337, 428, 3760, 293, 741, 486, 2073, 341, 382, 731, 295, 1164, 775, 439, 819, 3467, 295, 51725], "temperature": 0, "avg_logprob": -0.05112073295994809, "compression_ratio": 1.7758007117437722, "no_speech_prob": 2.454627213294147e-12}, {"id": 111, "seek": 66478, "start": 664.78, "end": 671.1, "text": " use cases from an agentic perspective it also does computer use it definitely writes code all of these", "tokens": [50365, 764, 3331, 490, 364, 9461, 299, 4585, 309, 611, 775, 3820, 764, 309, 2138, 13657, 3089, 439, 295, 613, 50681], "temperature": 0, "avg_logprob": -0.05589506166790603, "compression_ratio": 1.826241134751773, "no_speech_prob": 2.96160405227619e-12}, {"id": 112, "seek": 66478, "start": 671.1, "end": 675.3399999999999, "text": " things are something which which they have actually explained right so multimodal is something which we", "tokens": [50681, 721, 366, 746, 597, 597, 436, 362, 767, 8825, 558, 370, 32972, 378, 304, 307, 746, 597, 321, 50893], "temperature": 0, "avg_logprob": -0.05589506166790603, "compression_ratio": 1.826241134751773, "no_speech_prob": 2.96160405227619e-12}, {"id": 113, "seek": 66478, "start": 675.3399999999999, "end": 681.3399999999999, "text": " saw live again hopefully this was helpful it added some extra knowledge to your existing knowledge base", "tokens": [50893, 1866, 1621, 797, 4696, 341, 390, 4961, 309, 3869, 512, 2857, 3601, 281, 428, 6741, 3601, 3096, 51193], "temperature": 0, "avg_logprob": -0.05589506166790603, "compression_ratio": 1.826241134751773, "no_speech_prob": 2.96160405227619e-12}, {"id": 114, "seek": 66478, "start": 681.3399999999999, "end": 685.42, "text": " let me know if you guys have any questions and what do you feel after trying this thank you very much", "tokens": [51193, 718, 385, 458, 498, 291, 1074, 362, 604, 1651, 293, 437, 360, 291, 841, 934, 1382, 341, 1309, 291, 588, 709, 51397], "temperature": 0, "avg_logprob": -0.05589506166790603, "compression_ratio": 1.826241134751773, "no_speech_prob": 2.96160405227619e-12}, {"id": 115, "seek": 66478, "start": 685.42, "end": 689.3399999999999, "text": " for your time if you like the video please hit that like button and if you're new here please hit that", "tokens": [51397, 337, 428, 565, 498, 291, 411, 264, 960, 1767, 2045, 300, 411, 2960, 293, 498, 291, 434, 777, 510, 1767, 2045, 300, 51593], "temperature": 0, "avg_logprob": -0.05589506166790603, "compression_ratio": 1.826241134751773, "no_speech_prob": 2.96160405227619e-12}, {"id": 116, "seek": 68934, "start": 689.34, "end": 702.94, "text": " subscribe button as well thank you for watching and i will see you in the next one", "tokens": [50365, 3022, 2960, 382, 731, 1309, 291, 337, 1976, 293, 741, 486, 536, 291, 294, 264, 958, 472, 51045], "temperature": 0, "avg_logprob": -0.24505922794342042, "compression_ratio": 1.1388888888888888, "no_speech_prob": 3.871913206721089e-12}], "language": "en"}