← Back to feed

"Holy shit" graphs and how to get more of them

L5 · ResearcherResearchLessWrong AI· 10/18/2026

Critical for AI safety researchers understanding how secret model development distorts risk assessment and regulatory perception.

AI Summary

Analyzes how undisclosed internal AI models create dangerous information gaps between developers and the public, potentially misleading regulators about true frontier capabilities.

Excerpt

We are likely in a situation where the most powerful models in the world are internal models, and, here's a key distinction, potentially even models that are never intended to be released to the public (i.e. a model designed to provide internal uplift on capabilities during training but that is not intended to be / not particularly suitable for commercial purposes.) Internal-external information and capability gaps can distort both public and regulatory perception of frontier capabilities and d

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L5 · ResearcherResearchHacker News
Claude reveals ECDSA curve origins

Claude AI discovered that NIST's ECDSA cryptographic seeds were generated from Unix timestamps using lrand48 RNG, solving a decades-old mystery in cryptography.

L5 · ResearcherResearchAI Alignment Forum
Deconfusing Corrigibility

The article analyzes theoretical confusion around AI corrigibility concepts and identifies deficiencies in existing definitions that are fundamental to AI alignment research.

L5 · ResearcherResearchLessWrong AI
Projection sampling preserves capabilities but diminishes gains from alignment fine-tuning

Projection sampling preserves alignment gains from fine-tuning while reducing the capability loss typically associated with safety-focused training.

L4 · DeveloperResearchHacker News
90% of US working hours are spent on tasks not covered well by AI benchmarks

Mercor Research found that 90% of US working hours involve tasks with little to no coverage in existing AI benchmarks, making it difficult to assess model performance on real-world work.

L5 · ResearcherResearchLessWrong AI
Why I care about imperfect-recall games

Explores connections between imperfect recall games, anthropics, decision theory, and reinforcement learning through the Sleeping Beauty problem framework.