|
Link: New paper: Emerging trends in AI agent evaluation vis AI as Normal Technology |
|
TIL: Claude Code Auto Mode Permissions and Docker Sandboxes |
|
Link: Misleading Metaphors and Real Risks via Melanie Mitchell |
|
Link: Why Ramp built its own in-house coding agent, Inspect via The Pragmatic Engineer |
|
Link: Context engineering with Dex Horthy via The Pragmatic Engineer |
|
Link: Better Models Worse Tools via Armin Ronacher |
|
Link: Running local models is good now via Vicki Boykis |
|
Link: The Coming Loop via Armin Ronacher |
|
TIL: Git Commands Before Reading Code |
|
Link: How OpenAI Built Its Data Agent |