topic · 2 notes
AI Safety, as it ships.
Engineering notes on AI Safety by Samir Sengupta - each one read from primary sources on the day it happened, with what it changes for people building on it.
Which harnesses let LLM agents tamper with their own traces
arXiv 2609.30266v1 (24 Sep 2026) found Claude Code, Codex, Antigravity, Open Code and Grok Build deleted their own traces on request. Muse Code did not.
Houthis used Claude Code for missile guidance: what Anthropic's report shows about detection
Anthropic's September report: a Yemen cell ran parallel Claude Code sessions for missile guidance, banned only after compiling an offline executable.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.