Yoav Goldberg: Interpretability doesn't necessarily need baselines or tasks
yoavgo · x · 2026-08-27
In a discussion about "actionable interpretability", Yoav Goldberg disagrees with the notion that "baselines", "tasks", or "evals" are mandatory. He argues for rigor and supporting arguments for results/claims, but opposes restricting interpretability research to frameworks that require actionable metrics or specific tasks.
More from Safety
- A 22-member FSMB workgroup is quietly writing the rules for autonomous clinical AI — mattlungrenMD · 2026-10-15
- FTC sends 50-page civil investigative demands to OpenAI and Anthropic — GaryMarcus · 2026-10-15
- Evilginx Releases Free Chrome Extension for Faster Session Cookie Testing — evilsocket · 2026-10-15
- KV cache poisoning: an overlooked attack surface in LLM serving — lee_stott · 2026-10-15
- OWASP publishes Non-Human Identities Top 10 for securing machine and AI agent identities — gleech · 2026-10-15
- Founders petition EU leaders: negotiations are gutting the single digital standard — PMinervini · 2026-10-15