Researcher Questions Asking LLMs to Explain Their Own Reasoning
rajiinio · x · 2026-09-01
AI researcher Rajiinio expressed skepticism about studies that ask large language models to "explain their own reasoning." He compared the practice to asking a five-year-old to explain itself and taking the response seriously, implying that LLM self-explanations are often unreliable or logically unsound.
More from Safety
- Bitsec subnet outperforms Anthropic's hardened Fable 5 in bug detection — markjeffrey · 2026-09-01
- Sony, Warner Music sue Anthropic over training songs — fallingdowndizzyvr · 2026-09-01
- Prerequisite for Agent attacks: breaking out of the sandbox — voooooogel · 2026-09-01
- Webinar: Tackling authentication challenges in autonomous offensive security with AI agents — moyix · 2026-09-01
- Debate: Are LLMs Hacking Tools or Superhuman Attack Swarms? — joshua_saxe · 2026-09-01
- Technical Measures Proposed to Prevent Rogue AI Code Merges — peterwildeford · 2026-09-01