rohit

Great talk on Product strategy. #websummit blog.intercom.io/talk-product-s…

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it to prepare a customer brief, untangle your calendar, draft a report, or triage a Slack alert. It works across your files and everyday tools, produces the deliverable, and checks in before doing anything consequential. OpenWorker runs on your Mac, with Windows support coming soon. It does not lock you into any one model. Bring your own API key and run it with GPT 5.6 Sol, Claude Fable, Gemini 3.6, an open weight model (like Kimi, GLM, DeepSeek, Inkling), or Ollama to keep your data local. Your data does not leave your machine except through an LLM provider and integrations that you choose. @rohitcprasad and I are building OpenWorker because AI coworkers are an important way to get work done, and we want there to be an open, privacy-preserving, model-independent option. Check it out and let us know what you think! Try it out: openworker.com (requires your own API key) Source code: github.com/andrewyng/open…

@nishantpatel9 @AndrewYNg Please open an issue on GitHub so we can take a look and fix. Thanks

@AndrewYNg unable to add custom providers for LLM - on macOS. @rohitcprasad @AndrewYNg

Grok 4.5 is not quite as good as Fable, but it is very fast, cost-effective and gets the job done

It's over. Claude Design is generating insane UI, designs & animations from just text. Design will never be the same 🤯 10 wild examples:

a masterclass in coding agents from the head of anthropic. there’s still a tonne of leverage in knowing how to use these systems optimally and this is the best i’ve seen. make sure to bookmark so you can watch again and again chat

there are many types of intelligence. which type do we want models to have? yesterday i was analyzing agent trajectories in our rl envs and digging into tool-calling performance (how models use functions): > gpt-5 made 10x fewer errors than every other model! > claude made 10x more errors – but it reflected on its errors and fixed them. and so even though its initial tool calls were much worse, its final performance was close to gpt-5’s. this shouldn't be possible under the standard paradigm. in rl, we're taught that only outcomes matter: the reward signal, the final state, the destination. but that’s why i love digging into individual trajectories to understand what’s going on. gpt-5 embodies precision intelligence: flawless execution, doesn't make the mistake in the first place. claude embodies adaptive intelligence. it makes errors… but possesses something possibly rarer? the wisdom to notice and correct them? it’s like that friend who shows up perfectly dressed, says exactly the right thing, never spills their drink vs. the one who trips walking in, knocks over a plant, makes a joke, and everyone laughs. both are intelligent. which is better? i don't know. but claude's error-recovery patterns seem closer to metacognition. it's monitoring its execution and thinking about its thinking. gpt-5 may not need this layer right now. its first-order thinking is so accurate that it doesn’t need to reflect. maybe that's fine enough right now, when problems are straightforward enough to one-shot. but what about when they're not? (note: i don't know if gpt-5 is equally good at error-recovery when it needs to be. maybe it is! but i've noticed claude's recovery capabilities in the past.) in an increasingly complex world, where problems get harder and harder, i wonder if resilience will matter more than perfection? do you want the model that never falls, or the model that knows how to stand back up?

Wow! Grok analyzed the 1890 Thomas Edison lightbulb patent. Determined a better filament design and lit up the light. This emergent intelligence is found in no other AI model. It is fascinating and portends to the ability to not only change education but allow robots to build!

@HritikGuptaAI YT

YouTube is not luck. If you start today, you can earn $9000 per month by December 2025. I usually charge $73 for this proven guide, but for today, it's yours 100% FREE. Like and reply 'YT' and I'll send you my complete guide for FREE. Must follow me to get DM. FREE for 24 hrs

@wanneracademy 11

Want to get ElevenLabs for 98.88% cheaper? (not joking) Comment "11" and I'll send it to you! Must like + follow so I can DM you

"Claude Code is not just for coding. It's an AI agent that can do whatever you want it to do." Here's my new tutorial with @alexfinn where he showed me exactly how to build a life OS with Claude Code in 25 minutes. He saves 2+ hours daily using: ✅ /researcher to analyze competitors ✅ /daily_brief to get AI news every morning ✅ /brain_dump to find patterns from notes His setup uses slash commands and sub-agents and honestly blew my mind 🔥 Watch the full tutorial to learn how to set up a life operating system for yourself. 📌 Watch now: youtu.be/D0nDWQdN3F4N Also available on: Spotify: creators.spotify.com/pod/profile/pe… Newsletter: creatoreconomy.so/p/full-tutoria…

This ChatGPT prompt is literally $500/hr consultant🤯

Since DeepSeek R1's release, very quickly AWS, Azure, Fireworks AI, Groq, Hugging Face, SambaNova and Together AI all started to host R1 variants. What's the "best" model changes frequently, and so developers often want to try out new ones. The aisuite package, which helps developers do this quickly with minimal code changes. Thanks Rohit Prsad & team for working with me on this! github.com/andrewyng/aisu…

For many, DeepSeek's rise was unexpected. But what can we learn from prior internet waves about what might happen next? @martin_casado and @stevesi joined the a16z Podcast to discuss what drove the DeepSeek frenzy and more importantly, what we should take away, through the lens of Internet history. Full episode here: youtu.be/7lfTewdP1c4?si…

Understanding new .cursor/rules in 0.45 I've seen so many people struggling with .cursorrules and with the new .cursor/rules directory. Here is a Guide for you! 🧵

Announcing new open-source Python package: aisuite! This makes it easy for developers to use large language models from multiple providers. When building applications I found it a hassle to integrate with multiple providers. Aisuite lets you pick a "provider:model" just by changing one string, like openai:gpt-4o, anthropic:claude-3-5-sonnet-20241022, ollama:llama3.1:8b, etc. pip install aisuite Open-source code with instructions: github.com/andrewyng/aisu… Thanks to Rohit Prsad, Kevin Solorio, @standsleeping, Jeff Tang and @Johnsanterre for helping build this!

At Chroma - we are hiring our first product engineer. You will work directly with me and @MadelineNotes. You must have a great eye for functional, high-performance, and beautiful products. In-person in SF, DM me to learn more

@subnetmarco @martin_casado @ayyar Its confusing - how to interpret market share of Bedrock, Azure, others - they offer Llama, Claude, Mistral, OpenAI. Downloaded the pdf report from kong but it mentions nothing about how its computed. Super useful if it can be broken down per model & per provider.

These are results of a survey where around 750 developers and business leaders answered about their usage of AI. Organizations are most likely using more than one technology across the board, but nevertheless this is indicative of the dominance that OpenAI and Azure have when it comes to adoption and mindshare in the industry. The aggressive turn around of Gemini has been surprising (at least to me), and I see the lagging adoption of Bedrock interesting, at least in the mindshare of the people we surveyed. While these are survey results, the results are consistent with the actual usage data we are seeing across our AI gateway installations.

Survey results of nearly 800 enterprise folks on LLM market share (run by Kong). Most notable to me is the dramatic gain in Gemini use. Amazing job by the Alphabet team.