Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Stop using your agent logs just for debugging. Use them to train your own model. Today we're launching Agnost AI (YC S26)'s first model: agnost-*******-0.1 Trained for our first customer on their existing production traces & it beat the frontier: +22.9% task success −90.2% latency −94.5% cost If you... show more

shubham

3,853 subscribers

696,344 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

47 Comments

shubham1 month ago

We're live at

dhruvieiei1 month ago

we’ve been cookinggg

shubham1 month ago

cooking is an understatement

Chen Avnery1 month ago

most of my agent logs are the agent being confidently wrong and me quietly fixing it somewhere the log never sees.

shubham1 month ago

get agnosted

Saksham1 month ago

sick, we are daily users!

shubham1 month ago

cardboard getting better 10% every day

hari_haran1 month ago

lessgooo bois!!

shubham1 month ago

lfg indeed

William Lindholm🎂1 month ago

Congrats on launch! The speed you’re moving st is insane!

Arlan1 month ago

cool

Alexander Ren1 month ago

Super cool! Also love the launch video

shubham1 month ago

thanks alex

Aneesh Panda1 month ago

this is crazy, congratulations on the launch folks!

nikhil · sys/quests1 month ago

helll yeahhh!!

shubham1 month ago

hell yeah indeed

Ziyan Karmali1 month ago

@elonmusk you need this for @bot trust me

Frank Lee1 month ago

love agnost

Pratyush Rai1 month ago

Congrats on the launch Shubham. Wishing you the best. Looking forward to trying Agnost AI hopefully soon.

Harsh Savergaonkar1 month ago

insane!! lessgoooo 🤯

Ajit Sadalagi1 month ago

@Scobleizer I wish there was a way to train the model on the fly. Every time I acquire new data or knowledge, the model should be trained within a few minutes.

Agrit Tiwari1 month ago

🔥

Bek1 month ago

Congrats, best team

annaaa1 month ago

lessgoooo 🚀

shubham1 month ago

lfg indeed

Hasan (3dblur)1 month ago

bangers

Danylo Borodchuk1 month ago

Fire

Chetan1 month ago

Lfggg!!!

shivansh1 month ago

no wayyyy 🤯🤯 this is sooo goodd

shubham1 month ago

thanks joshi

sam1 month ago

Okei

Hai Ta1 month ago

This is very cool congrats on the launch!!

shubham1 month ago

thanks hai ta!

harsh1 month ago

Fire!!🔥

Vir1 month ago

the team is cooking hard

aman1 month ago

So cool! Congrats on the launch guys 🚀

shubham1 month ago

thanks aman

fj_nm | AI Systems & Automation1 month ago

Production traces are already the best training set most teams ignore. Logs stop being waste and become the moat. Curious how you filter noisy traces before fine-tune — that step decides if the model learns your process or your bugs.

Parvez Shaikh1 month ago

Congrats on the launch , those latency and cost numbers are impressive. Curious to see how this scales across more use cases.

Parth1 month ago

congrats on the launch!

shubham1 month ago

thanks parth

Ayush Pandey1 month ago

Lesss gooo Congratulations guys!!!!

Nick Khami1 month ago

lfg

shubham1 month ago

lfg indeeed

Anthony K1 month ago

Agent logs are usually buried in observability and never turned into a signal. Training on production traces makes sense. How do you avoid feedback loops when the improved agent changes the trace distribution?

Piyushh1 month ago

🚀🚀🚀

Bhoomika1 month ago

lesgooo, congrats guys

Related Videos

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

“don’t train your own model” is common ai advice. it's wrong. your token bill's the proof. today, we’re excited to launch castform into open preview. castform is the easiest way for you to train your own model, on your own data. open-weights models are performant and much cheaper. when trained on your task & proprietary data, they beat closed models. the thing standing between you and that was weeks of plumbing & years of ml expertise. with castform, model training is as simple as prompt engineering. castform bring your agent traces or raw corpora. castform turns it into training data, picks the right algorithmic recipes, manages gpus, and gives you an ide to watch and chat with your model as it learns. see what you can build with castform👇

girish

463,114 views • 3 months ago

Your perfect model is always ready. With Fotor, you can create your own AI model and use it to bring your marketing ideas to life. Generate consistent photos, videos, and campaign assets without the time and cost of traditional photoshoots. One AI model. Endless content. Create your model. Build your brand. Market smarter. Try Fotor AI Today！

Fotor

45,843 views • 2 months ago

Stop paying for three AI subscriptions just to use the best models. One private platform gives you all of them, and it never records your prompts. Use chat, images, video, even a video editor. Every frontier model, live on Part 6: The AI Talk

Stop paying for three AI subscriptions just to use the best models. One private platform gives you all of them, and it never records your prompts. Use chat, images, video, even a video editor. Every frontier model, live on Part 6: The AI Talk

OpenGradient (∇, ∇)

14,683 views • 2 months ago

Excited to announce that Aamir Poonawalla and I are launching @understudylabs as part of Y Combinator 's S26 batch. We help you cut your company’s Anthropic bill by 80% with no loss of performance. Understudy is an inference cloud. We capture your AI traces, train smaller models, and automatically deploy them (only when they outperform the expensive model you are currently paying for). Instead of renting the same frontier model forever, your AI infrastructure gets cheaper and better every time it runs.

Excited to announce that Aamir Poonawalla and I are launching @understudylabs as part of Y Combinator 's S26 batch. We help you cut your company’s Anthropic bill by 80% with no loss of performance. Understudy is an inference cloud. We capture your AI traces, train smaller models, and automatically deploy them (only when they outperform the expensive model you are currently paying for). Instead of renting the same frontier model forever, your AI infrastructure gets cheaper and better every time it runs.

Luis Manrique

50,331 views • 2 months ago

Factory benchmarks let you build your own model bench using your past coding agent runs. - Mirrors your environment, secrets, and MCPs for each run - Scores output on judging criteria you define - Generates a report with model recs using cost vs. quality Here's how it works:

Factory benchmarks let you build your own model bench using your past coding agent runs. - Mirrors your environment, secrets, and MCPs for each run - Scores output on judging criteria you define - Generates a report with model recs using cost vs. quality Here's how it works:

Warp

72,768 views • 1 month ago

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-specific grading to improve model performance—especially useful for complex domains. Take Accordance, which used RFT to fine-tune a model that’s SOTA for their tax and accounting purposes. And in supervised fine-tuning news: you can now fine-tune GPT-4.1 nano. Get even more from our fastest, cheapest model by training it specifically for your use-case.

OpenAI Developers

667,248 views • 1 year ago

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Create your own local and free AI agent using an open source model You can combine: - IBM's Granite 3.3 8B AI model - LM Studio to run it on a laptop - Smolagents to build your agent Small AI models are now powerful enough to run an autonomous agent. Thanks to IBM France for sponsoring this content!

Paul Couvert

18,890 views • 1 year ago

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Veeral Patel

1,428,159 views • 1 month ago

Stop hardcoding one model name in your code. Now you can give each request a policy: a small rule for what the call needs It picks the right model for the job, on your own keys This is unhardcoded, our new open source routing for AI models, live today

Stop hardcoding one model name in your code. Now you can give each request a policy: a small rule for what the call needs It picks the right model for the job, on your own keys This is unhardcoded, our new open source routing for AI models, live today

GenLayer

97,224 views • 3 months ago

.L3Harris says Palantir helped them beat frontier AI models in less than 2 days, at 95% lower cost: "When we fine-tuned open source models trained on our own data, we were able to outperform the frontier models in less than 48 hours." "The cost of our fine-tuned open source model was 95% lower than the frontier models we were using." "AI is a commodity. It's all about the data. We view our data as a corporate asset. It's our unique hard-earned knowledge." "We believe American defense companies should not be a vassal for frontier AI labs, handing over our data and institutional knowledge, hoping to rent back the intelligence it creates." " We own the model, we own the compute, we own the advantage."

.L3Harris says Palantir helped them beat frontier AI models in less than 2 days, at 95% lower cost: "When we fine-tuned open source models trained on our own data, we were able to outperform the frontier models in less than 48 hours." "The cost of our fine-tuned open source model was 95% lower than the frontier models we were using." "AI is a commodity. It's all about the data. We view our data as a corporate asset. It's our unique hard-earned knowledge." "We believe American defense companies should not be a vassal for frontier AI labs, handing over our data and institutional knowledge, hoping to rent back the intelligence it creates." " We own the model, we own the compute, we own the advantage."

Jawwwn

1,105,305 views • 25 days ago

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

OpenAI engineer explained every form of fine-tuning in 1 hour 46 minutes - better than $3000 fine-tuning bootcamps. pick your task -> try prompting first -> drop to SFT for style -> run DPO for preference -> run RFT for verifiable rewards -> ship a model 10x cheaper than GPT-5. That loop is why teams that fine-tune beat teams that only prompt on cost and speed. Prompting + SFT + DPO + RFT + OpenAI fine-tuning API - that's the stack. Watch and save it, then pick the right fine-tune for your task this week.

h100envy

41,245 views • 2 months ago

Launching today: the world’s first fully optimized LLM routing stack that can be embedded directly into your product, Merge Embedded Routing Stack. Model sovereignty is now table stakes for any AI product. Users and companies are demanding full control over the AI models running in your product. Right now, no company is able to do this without massive overhead. Until today. Merge makes it easy for your customers to use your product exactly the way they want to. With a single API, you can: 1. Allow customers to bring their own keys, manage their own budgets, and set policies like fallback rules, model allowlists, and more 2. Let each customer connect and switch their own models, right inside your product 3. Optimize each customer for cost, performance, or capability Without Merge, you’d be: - Building routing policies, provider integrations, and LLM key management - Giving your users zero model independence - Receiving endless customer support tickets asking “can I use 5.6 Sol?” Products that fight their customers' model strategy will lose to products that fit it. Merge is the only place that allows your users to produce the exact results they want, with the models they have access to. Give your customers the advantage, without the massive overhead costs.

Launching today: the world’s first fully optimized LLM routing stack that can be embedded directly into your product, Merge Embedded Routing Stack. Model sovereignty is now table stakes for any AI product. Users and companies are demanding full control over the AI models running in your product. Right now, no company is able to do this without massive overhead. Until today. Merge makes it easy for your customers to use your product exactly the way they want to. With a single API, you can: 1. Allow customers to bring their own keys, manage their own budgets, and set policies like fallback rules, model allowlists, and more 2. Let each customer connect and switch their own models, right inside your product 3. Optimize each customer for cost, performance, or capability Without Merge, you’d be: - Building routing policies, provider integrations, and LLM key management - Giving your users zero model independence - Receiving endless customer support tickets asking “can I use 5.6 Sol?” Products that fight their customers' model strategy will lose to products that fit it. Merge is the only place that allows your users to produce the exact results they want, with the models they have access to. Give your customers the advantage, without the massive overhead costs.

Shensi Ding

357,497 views • 2 months ago

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,962 views • 3 years ago

We’re launching Optima. Now anyone can create a custom benchmark for their use case, leveraging Artificial Analysis’ leading research and platform Building and running benchmarks is difficult. We have distilled Artificial Analysis’ research and experience developing benchmarks into Optima, a new platform for benchmarking models on your own workloads and comparing performance, speed and cost efficiency. Optima allows you to find the best model for your task, or an equally performant alternative to your current setup at 10x lower cost or time per task. We’ve integrated Artificial Analysis' research and experience in benchmarks across the Optima workflow: ➤ Build benchmarks based on your own data and use cases: There are three ways to build a benchmark with Optima. Upload an existing evaluation dataset from your own files or Hugging Face, or import agent traces from platforms including Arize AI, Braintrust and langfuse.com. Install the Optima skill to build a benchmark using context from your coding environment and previous sessions. Or simply describe your use case and provide example inputs and outputs, and Optima will build the benchmark for you ➤ Run across the latest models: Run the same benchmark across leading models in a single click, and keep your leaderboard up to date as soon as new models are released ➤ Bring Artificial Analysis grading to your own benchmark: Evaluate responses against objective rubric criteria or using the same pairwise judging approach used for Artificial Analysis benchmarks including GDPval-AA and AA-Briefcase. For pairwise judging, select your preferred responses from a sample and Optima uses those preferences to rank models across your test set ➤ Compare performance, cost and time efficiency: Optima measures more than model performance. Cost per Task and Time per Task are tracked alongside benchmark scores, with category-level results and support for custom metrics, allowing you to compare the tradeoffs between models for your specific use case Ahead of launch, here are examples questions our beta testers answered with Optima: ➤ Which model can save me 10x the cost without a meaningful decrease in quality for my finance & accounting agent? ➤ Which model best matches the writing style of lawyers for my legal agent? ➤ Which model can best identify different elements in my custom image dataset? Optima is available today. Build your own benchmark at

We’re launching Optima. Now anyone can create a custom benchmark for their use case, leveraging Artificial Analysis’ leading research and platform Building and running benchmarks is difficult. We have distilled Artificial Analysis’ research and experience developing benchmarks into Optima, a new platform for benchmarking models on your own workloads and comparing performance, speed and cost efficiency. Optima allows you to find the best model for your task, or an equally performant alternative to your current setup at 10x lower cost or time per task. We’ve integrated Artificial Analysis' research and experience in benchmarks across the Optima workflow: ➤ Build benchmarks based on your own data and use cases: There are three ways to build a benchmark with Optima. Upload an existing evaluation dataset from your own files or Hugging Face, or import agent traces from platforms including Arize AI, Braintrust and langfuse.com. Install the Optima skill to build a benchmark using context from your coding environment and previous sessions. Or simply describe your use case and provide example inputs and outputs, and Optima will build the benchmark for you ➤ Run across the latest models: Run the same benchmark across leading models in a single click, and keep your leaderboard up to date as soon as new models are released ➤ Bring Artificial Analysis grading to your own benchmark: Evaluate responses against objective rubric criteria or using the same pairwise judging approach used for Artificial Analysis benchmarks including GDPval-AA and AA-Briefcase. For pairwise judging, select your preferred responses from a sample and Optima uses those preferences to rank models across your test set ➤ Compare performance, cost and time efficiency: Optima measures more than model performance. Cost per Task and Time per Task are tracked alongside benchmark scores, with category-level results and support for custom metrics, allowing you to compare the tradeoffs between models for your specific use case Ahead of launch, here are examples questions our beta testers answered with Optima: ➤ Which model can save me 10x the cost without a meaningful decrease in quality for my finance & accounting agent? ➤ Which model best matches the writing style of lawyers for my legal agent? ➤ Which model can best identify different elements in my custom image dataset? Optima is available today. Build your own benchmark at

Artificial Analysis

133,443 views • 1 month ago

Gpt-6-astra is OpenAI’s latest model. Astra is said to be their most intelligent model so far, with frontier leading capabilities for computer use. Have you tried it? What are your thoughts so far? If you haven’t, give it a try in Pi today!

Gpt-6-astra is OpenAI’s latest model. Astra is said to be their most intelligent model so far, with frontier leading capabilities for computer use. Have you tried it? What are your thoughts so far? If you haven’t, give it a try in Pi today!

Pi

29,305 views • 27 days ago

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

Livestream Alert: Open World Models in Production: LTX.io and ComfyUI Founders Live A special live conversation with Yoland Yan ( CEO, ComfyUI ) & comfyanonymous ( Founder, ComfyUI ) and Zeev Farbman ( CEO, LTX ) Join us as we sit down with the teams behind LTX and ComfyUI to talk about building an open world model that integrates natively into the production tools creators use. We'll explore what it took to build LTXa foundational model that understands space, motion, and how the physical world operates—with synchronized video and audio generation, truly open weights, and the flexibility to fine-tune on your own data. We'll explore what it took to ship a frontier video model in the open, how LTX and ComfyUI are building the pipeline for AI-driven production together, and what it means for creators, developers, and the wider open-source ecosystem. What we'll cover: → LTX: the open world model for synchronized video + audio, and beyond → Native integration into ComfyUI workflows and production pipelines → Open world models vs. closed platforms and where things are headed → Fine-tuning LTX on your own data with LTX Trainer → Community Q&A — bring your questions

ComfyUI

13,174 views • 2 months ago

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket TTS training stack: data pipeline, recipes, and evals. It learns pretty damn fast: ~15k steps: babbling starts turning into words ~50k steps: it reads anything you type (WER under 1%) ~200k steps: the voice stops sounding synthetic On a beefy consumer GPU, that's a week of training. On eight H100s: 10-20 hours. A TTS training run will cost you less than $200 if you rent your hardware, and an order of magnitude less if you just pay for power. Some things we'd love to see people try: - Train it in your own language (a few hundred hours of speech gets you surprisingly far). - Add new features to Pocket TTS (Emotion tags? Make it sing?). - Beat us at our own game: make it faster and smaller. Show us what you build! We'll highlight the best models and new languages for the whole community to enjoy. Pocket TTS has already found many use cases, from reading for people with visual impairments to making NPCs in video games talk, and we're sure there's much more to do with it! Here's an example of a Czech Pocket TTS. Try just asking your favorite agent to find data and apply the method, and you can have your own. Get started:

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket TTS training stack: data pipeline, recipes, and evals. It learns pretty damn fast: ~15k steps: babbling starts turning into words ~50k steps: it reads anything you type (WER under 1%) ~200k steps: the voice stops sounding synthetic On a beefy consumer GPU, that's a week of training. On eight H100s: 10-20 hours. A TTS training run will cost you less than $200 if you rent your hardware, and an order of magnitude less if you just pay for power. Some things we'd love to see people try: - Train it in your own language (a few hundred hours of speech gets you surprisingly far). - Add new features to Pocket TTS (Emotion tags? Make it sing?). - Beat us at our own game: make it faster and smaller. Show us what you build! We'll highlight the best models and new languages for the whole community to enjoy. Pocket TTS has already found many use cases, from reading for people with visual impairments to making NPCs in video games talk, and we're sure there's much more to do with it! Here's an example of a Czech Pocket TTS. Try just asking your favorite agent to find data and apply the method, and you can have your own. Get started:

kyutai

106,057 views • 1 month ago

If you need to fine-tune a model for your codebase, your code is bad. Agree or disagree? We talk AI hot takes in our latest GitHub Podcast episode. What would you add to the list? Listen wherever you listen to podcasts or find it here

If you need to fine-tune a model for your codebase, your code is bad. Agree or disagree? We talk AI hot takes in our latest GitHub Podcast episode. What would you add to the list? Listen wherever you listen to podcasts or find it here

GitHub

43,648 views • 18 days ago

Here is EVERY AI tool you need to be using in August 2026 I've personally used each for 100+ If you master them and use them all, you'll be a productivity MACHINE The list of the tools are down below. How to use each is in the video! • Best planning model: Fable 5 medium- smartest model out there. Use it to do all your ideation and planning • Best execution model: ChatGPT 5.6 sol medium- best bang for your buck. TONS of usage and incredibly smart • Best AI tool: ChatGPT Voice: the future of interfacing with technology • Best AI agent harness: ChatGPT Desktop app- can do anything any other AI agent can do, but does it better • Best model for building UI/UX/games: Claude Code w/ Claude Opus 5- this model gets a lot of hate. Some of it warranted, most of it not. NOTHING beats Opus 5 for UI • Local model: Qwen 3.6 27b on DGX Spark- best speed and intelligence ratio in local AI • Other must have tools: Buzz from Jack Dorsey. The future of AI is multiplayer, and this is the first true multiplayer AI platform out there

Here is EVERY AI tool you need to be using in August 2026 I've personally used each for 100+ If you master them and use them all, you'll be a productivity MACHINE The list of the tools are down below. How to use each is in the video! • Best planning model: Fable 5 medium- smartest model out there. Use it to do all your ideation and planning • Best execution model: ChatGPT 5.6 sol medium- best bang for your buck. TONS of usage and incredibly smart • Best AI tool: ChatGPT Voice: the future of interfacing with technology • Best AI agent harness: ChatGPT Desktop app- can do anything any other AI agent can do, but does it better • Best model for building UI/UX/games: Claude Code w/ Claude Opus 5- this model gets a lot of hate. Some of it warranted, most of it not. NOTHING beats Opus 5 for UI • Local model: Qwen 3.6 27b on DGX Spark- best speed and intelligence ratio in local AI • Other must have tools: Buzz from Jack Dorsey. The future of AI is multiplayer, and this is the first true multiplayer AI platform out there

Alex Finn

42,136 views • 1 month ago