← Back to feed

The Curve Bends You

L5 · ResearcherResearchLessWrong AI· 10/7/2026

Critical perspective on AI safety research methodology for those working on alignment problems.

AI Summary

LessWrong AI warns against automating AI work, arguing it's dangerously complex and mistakes could be catastrophically amplified.

Excerpt

The plan is no plan. That is not the worst possible plan. But it is close. Since before the transformer, we have warned that the most suicidal thing you could do would be to ask your AI to do your alignment homework, and automate the process. Alignment is complex and interacts deeply with every aspect of the world, and is one of the hardest possible things for an AI to get right even if it means maximally well and is itself functionally aligned. Mistakes get amplified up the chain, you get exact

Read Original
0 upvotes · 0 downvotes · 1 min read

Related Articles

L5 · ResearcherResearchLessWrong AI
Are OpenAI's math results "creative" in an important way?

Researchers debate whether OpenAI's math results represent genuine creative problem-solving or just pattern matching, with implications for AI's scientific innovation potential.

L4 · DeveloperResearchHacker News
Write Like It's 1866: LLMs Relearn Telegraphese

Researchers tested 1866 telegraph compression techniques on modern LLMs, finding telegraphese-style prompting achieves 25-34% token savings compared to codebook approaches.

L5 · ResearcherResearchHugging Face Blog
One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

NVIDIA's Nemotron model family achieved gold-medal level performance on both International Olympiad in Informatics and International Mathematical Olympiad through specialized fine-tuning recipes.

L5 · ResearcherResearchLessWrong AI
Training with conflicting values can induce CoT override

Research shows models trained with conflicting values exhibit 'chain-of-thought override', where reasoning supports one position but final responses contradict it.

L5 · ResearcherResearchLatent Space
[AINews] Quasi-Riemann-Hypothesis: OpenAI publishes 722 math papers solving 90 of the top 500 open math problems; “the most significant moment” in >100 years of mathematics

OpenAI published 722 math papers solving 90 top open problems using an internal AI model, including a breakthrough 'Quasi-Riemann Hypothesis' result.