(If you're looking for videos of talks, go here.) Interviews *of* me (ie I was being interviewed) Interviews *by* me (ie I was the interviewer) Interviews of me (ie I was being interviewed) Let's sto…

Release: llm 0.32a2 A bunch of useful stuff in this LLM alpha, but the most important detail is this one: Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables interleaved reasoning across tool calls for GPT-5 class models. #1435 This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if y

Release: llm 0.32a2 A bunch of useful stuff in this LLM alpha, but the most important detail is this one: Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables interleaved reasoning across tool calls for GPT-5 class models. #1435 This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if y

Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read - MinishLab/semble

AI agents are acting as principals in IAM systems that weren't built for them. No stable identity primitives, no session-safe credentials, no RBAC for entities that can spawn sub-agents. When Mythos found thousands of CVEs autonomously with no attribution chain — that's what agent identity debt look