cd /news/large-language-models/ask-hn-what-is-one-simple-thing-llms… · home › topics › large-language-models › article
[ARTICLE · art-111163] src=news.ycombinator.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Ask HN: What is one simple thing LLMs are insanely bad at?

A Hacker News user asked what simple tasks large language models still fail at, citing keyword search as an example where models like ChatGPT and Claude struggle despite excelling at semantic search. The discussion highlights persistent limitations in basic, literal tasks.

read1 min views2 publishedAug 26, 2026

What is one simple thing you repeatedly ask ChatGPT, Claude, or another model to do that it still somehow messes up?

nhl toronto scores nhl hockey toronto scores "nhl hockey" toronto score today nhl "hockey score toronto" "hockey" who won toronto

etc.

Somehow being good at semantic search makes them bad at keyword search, for whatever reason.

reply

Oh, you said simple. Speaking like a human

source & further reading
news.ycombinator.com — original article What platform has the best AI CMO? Ask HN: Is "3D as software" about to undergo a Cambrian Explosion? Ask HN: Why do talentless hacks hate AI?
── more in #large-language-models 4 stories · sorted by recency
── more on @chatgpt 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/ask-hn-what-is-one-s…] indexed:0 read:1min 2026-08-26 · —