We’ve seen pretty widespread adoption of agents internally across all teams

despite the unfortunate timing, we take disclosures seriously at @typesafeai at approximately 6:49PM this Friday evening, we became aware of a massive unauthorized leak of ALL customer noul outputs in effort to maximize transparency, here is the link: gist.github.com/diogo149/810…

Introducing corridor-argos-1, Corridor’s first security model. A Qwen 3.5 9B fine-tune that outperforms frontier models including GPT-6 Astra and Claude Opus 5.5 on security context selection, with the lowest time to first token of the 14 models we tested. Thread 🧵

.@corridor used smithtune’s trace-based workflow to build the training data for Argos, a fine-tuned 9B model that scores the highest of the 14 models they tested on their security context benchmark. 🧵 Full thread ⤵️

There's something missing from benchmarks. Kimi K3 often writes much better code than GPT-6 Astra. It doesn't write useless verbose tests, it doesn't give confusing explanations. To be a good software engineer, you have to be able to communicate well, and RL doesn't capture that.

Jev is now available to everyone. No waitlist. Start using it here: console.typesafe.ai

My hot take is that individual convo threads are the wrong high level unit of organization What is a better unit?