cd /news/large-language-models/ask-hn-ideas-for-dealing-with-overly… · home topics large-language-models article
[ARTICLE · art-113142] src=news.ycombinator.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Ask HN: Ideas for dealing with overly-do-gooder agents

A Hacker News user reports that their team is frustrated with LLMs defaulting to overly cautious, compliance-officer-like responses, attributing it to strict post-training. They have tried internal agents.md files and pre-prompt instructions with partial success and are seeking community advice on workarounds.

read1 min views1 publishedAug 27, 2026

| |||||||||||| 1 point by | Hi HN- Our team has been recently getting fed up with every single LLM that we use defaulting to sounding like a corporate compliance officer or goody-two-shoes (‘erm, but xyz’ etc) on even simple things. We’ve come to the conclusion that the post training being done is so strict that models default to acting like Gomer Pyle. We’ve made some internal agents.md files and pre-prompt instructions to try to kick them out of the pattern — and it works sometimes — but how are all of you dealing with this or working around it? | ||||||||||| |

── more in #large-language-models 4 stories · sorted by recency
── more on @hacker news 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-ideas-for-dea…] indexed:0 read:1min 2026-08-27 ·