Towards AI
Harness, Evals, Guardrails: I Built One Small Agent to Learn the Words Everyone Uses

Related reading
TechCrunch AI
Anthropic pitches AI safety bill that may block a model if 50+ people could be killed
TechCrunch AIHugging Face CEO warns that Netflix’s OpenAI hack documentary isn’t accurate
TechCrunch AIAnthropic’s cloud partnerships are getting messy
TechCrunch AISpaceX’s AI business is beating expectations