'Models get harder to understand with scale, not easier': new interp debate thread

NeelNanda5 · x · 2026-10-17

Interpretability researcher Neel Nanda endorses a new thread by Jacob Hilton arguing that language models are getting much harder to fully understand as they scale, not easier — a pointed contribution to the ongoing 'have we solved interp?' discourse in the alignment community.

Related event: ARC researcher argues we understand less than 0.01% of frontier models as interpretability debate reignites(21 posts)→

Original post →

More from Safety

• Sriram Krishnan, architect of the US AI Action Plan, to headline South Park Commons fireside chat — adityaag · 2026-10-17
• Open-licensed training data keeps growing: the 8TB Common Pile v0.1 — BlancheMinerva · 2026-10-17
• Surveillance talking points laundered as anti-AI; open training data still growing — BlancheMinerva · 2026-10-17
• Audit of 14,000 domains shows the AI data commons in rapid decline — BlancheMinerva · 2026-10-17
• EleutherAI's push to narrow the EU AI Act for open-source research — BlancheMinerva · 2026-10-17
• Broad AI crawler bans would gut the scraping tools newsrooms rely on — BlancheMinerva · 2026-10-17

Safety channel →