Our GTM agent is easily the single most widely used and loved agent we’ve built internally The GTM agent has: - saved reps >40hrs per month, each - lead-to-qualified-opportunity conversion rate up 250% - 50% of reps use it daily and 86% use weekly Want to work on similar https://t.co/5j0xDJMh2a
— Brace (@BraceSproul) Mar 9, 2026
https://t.co/9WLIjS8Lrk
— LangChain (@LangChain) Mar 9, 2026
🚨 Holy shit.. Karpathy just open-sourced a repo that lets AI agents run their own ML research experiments autonomously. 630 lines of code. Single GPU. No human in the loop. Every dot in his graph is a full LLM training run that took 5 minutes, and the agent just keeps going, https://t.co/Aunm5NKja4 https://t.co/RsPSgaR5uL
— Alex Prompter (@alex_prompter) Mar 9, 2026
What this means for non-developers: Claude Code now automatically reviews code changes before they go live. When someone submits new code, a team of AI agents checks it for bugs. The business application: automated quality control. Imagine this same concept applied to: → https://t.co/VIZjDH4fTn
— Corey Ganim (@coreyganim) Mar 9, 2026
Three days ago I left autoresearch tuning nanochat for ~2 days on depth=12 model. It found ~20 changes that improved the validation loss. I tested these changes yesterday and all of them were additive and transferred to larger (depth=24) models. Stacking up all of these changes, https://t.co/j34dSt4oht
— Andrej Karpathy (@karpathy) Mar 9, 2026
Alpha! https://t.co/QL8Irgp4Hf
— Marc Andreessen 🇺🇸 (@pmarca) Mar 9, 2026
interesting and hiring: @joannejang - gm of labs at openai ("inventing and prototyping new interfaces for how people collaborate with ai") - stanford bs mathematical & computational sciences and ms cs - interned with congressman Adam Schiff, at nasa jpl, at apple, at disney, and https://t.co/jJfFwTE3jy
— Chris Barber (@chrisbarber) Mar 9, 2026
