Ask HN: What is one simple thing LLMs are insanely bad at?
davidest · hn · 2026-08-26
The author is seeking ideas for training a specialized model and asks the community for examples of simple tasks that ChatGPT, Claude, or other LLMs consistently fail at.
More from Models
- Giga-Embeddings: Sparse 10B MoE encoder boosts throughput by 2.65x — _reachsumit · 2026-08-26
- Anthropic Readies Two New Claude Checkpoints for Release — ResultBackground2450 · 2026-08-26
- Meta expands Muse Spark 1.2 globally with 1M context at $0.10 per million tokens — qinzytech · 2026-08-26
- Users Report Degraded Readability in Fable and Opus Outputs — nrehiew_ · 2026-08-26
- Study finds LLMs susceptible to 'Prior-hacking', derailing reasoning — RexDouglass · 2026-08-26
- Dev calls for automatic model routing in Gemini API for cost and rate-limit fallback — EvanOtero · 2026-08-26