One-size-fits-all blanket usage caps on AI spend don’t make sense. On the other hand, yolo tokenmaxxing doesn’t scale either. We’ve come up ...

We productized how we handle incidents, bug reports, and alerts at @cognition with Devin Oncall. It’s completely changed how we work and als...

Visual Basic 6 running in the browser. Built on top of an OpenAI-like Intelligent/GenUI React DSL + WebGPU. (h/t @wieslawsoltes) https:/...

mise is really good. i switched from homebrew on my work machine and have had a wonderful experience so far https://twitter.com/jdxcode/stat...

ICYMI: you can now use @DevinAI with your @ChatGPT subscription. Once you link your account, your OpenAI model usage in your sessions count...

Cool write up of how a $200 Kev-4B fine-tune can mog every other decision model. If you want to do this yourself, there is an official ski...

agents hit diminishing returns when they saturate the available feedback loop

I’ve been experimenting with Devin and autoresearch every night for the past week or so. The prompt I’ve been using for is pretty simple: `...

new turing test: show me an agent that can cancel a subscription to Adobe Creative Cloud https://twitter.com/KevinPicchi/status/210749702849...

What you're seeing in gaming decompilation, stitching, reverse engineering and then ultimately web porting (via WASM and WebGPU) is a testam...

Wrote a post about Kev 1.0 and how it works https://jaredpalmer.com/blog/introducing-kev

Kev 1.0: an open weight family of decision models you can train and run on your own. • New Kev-27B + updated Kev-9B • 64k-token document ...

Kev-4B is now on @OpenRouter

Kev 27B full SFT run in flight. Should finish this evening

Triton kernel launches are the new useEffect

Been using @DevinAI to do autoresearch on Kev overnight with @Modal Outposts (this gives Devin’s Cloud agent full access to GPUs) as well as...

operating partner at major VC sent me a slop DM from their claw/agent. my immediate response was to prompt inject them for fun. fafo my dude

AI has shown us that agency is much rarer than we previously assumed

Kev has now been refactored on top of Qwen3.5. New checkpoints are now available at 0.8B, 4B, and 9B along with a fine-tuning script you c...

UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source Jev-like decision models you can train and run yourself...