LLMs Silently Accumulate Approximation Errors Without External Verification, Argues Engineer
gerardsans · x · 2026-09-19
In a discussion thread, Gerard Sans argues that since LLMs are distribution-based systems, they pass through phase transitions conditioned on inputs—from in-distribution, to sparse sampling, to fully out-of-distribution regions of the input space. Without strong external verification, users silently absorb approximation errors, which is compounded by the enormous output space and input-conditioned error behavior. His conclusion: external verification is mandatory, not optional.
Related event: Researchers Debate Silent Error Accumulation in LLMs Without Verification(3 posts)→
More from Models
- A writer on Claude, likely the unreleased Opus 5 — Sauers_ · 2026-09-19
- LLMs Are Smart but Not Sharp: A New Qualitative Lens on Model Progress — jmugan · 2026-09-19
- Moonshot's Kimi K3 lands on Amazon Bedrock with 1M-token context and prompt caching — emmanuelvivier · 2026-09-19
- Gemini's 11-option model picker draws user ire: 'If it's so smart, figure it out' — Fine_Vermicelli2826 · 2026-09-19
- ChatGPT Searched 74 Websites to Answer a Daylight Savings Question — dioscuri · 2026-09-19
- DeepSeek V5 Leak: Imminent Launch Could Match Top Closed Models, Staying Open-Weight — inductionheads · 2026-09-19