Ask HN: What is one simple thing LLMs are insanely bad at?
Sentiment Mix
Expert Signals
davidest
author • 1 mention
Hacker News
source • 1 mention
AI-Generated Claims
Generated from linked receipts; click sources for full context.
Ask HN: What is one simple thing LLMs are insanely bad at?.
Supported by 1 story
I am looking for ideas on what to train a specialized model for!What is one simple thing you repeatedly ask ChatGPT, Claude, or another model to do that it still somehow messes up?
Supported by 1 story
Related Events
Students prefer Gemini over ChatGPT and Claude for AI essays in blind tests
LLMs • 8/26/2026
AWeber Puts Its New AI Landing Page Builder Head-to-Head With Lovable and Claude, Not Other Email Platforms - Business Wire
LLMs • 8/26/2026
Longbridge integrates investment tools into ChatGPT and Claude platforms - Vietnam Investment Review - VIR
LLMs • 8/26/2026
Google Gemini 3.5 AI Launches Speech-to-Text Model - The Cryptonomist
LLMs • 8/26/2026
Five things to know about Anthropic ahead of Wall Street debut - France 24
LLMs • 8/26/2026
Causality Chain
Preceded By
Led To
Meta reportedly delays rollout of new AI model Avocado – here's why - Mint
55 causal score
Anthropic tells employees at its San Francisco office to work from home after it received a notice saying - The Times of India
55 causal score
Google just told OpenAI and Anthropic, we taking the 'lawyers route' to come after you - The Times of India
55 causal score