Vysogota
@petko.me
30 followers 6 following 970 posts
за днес толкова, вика, и този свят свърши 🌉 bridged from ⁂ social.petko.me/@petko, follow @ap.brid.gy to interact
за днес толкова, вика, и този свят свърши 🌉 bridged from ⁂ social.petko.me/@petko, follow @ap.brid.gy to interact
![Frustration detection via regex (yes, regex)
userPromptKeywords. ts contains a regex pattern that detects user frustration:
/\b(wtf [wth] £fs|omfg|shit(ty|tiest)?|dumbass|horrible|awful|
piss(ed|ing)? off|piece of (shit|crap|junk)|what the (fuck|hell)|
fucking? (broken|useless|terrible|awful [horrible)|fuck you|
screw (this|you)|so frustrating|this sucks|damn it)\b/
This was the most-discussed finding in the HN thread. The general reaction: an LLM
company using regexes for sentiment analysis is peak irony.
Is it ironic? Sure. Is it also probably faster and cheaper than running an LLM inference just
to figure out if a user is swearing at the tool? Also yes. Sometimes a regex is the right tool.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:fotof4iyols6wiqvuj5cs2mv/bafkreifh5nfvz2lcaunt7irxab4s64i5zfmxsvucdsygmu7zm5ga2qruwq)
![console.log([1, 5, 10, 100].sort())
returns Array(4) [ 1, 10, 100, 5 ]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:fotof4iyols6wiqvuj5cs2mv/bafkreihjbsbjkgvo65kogx3phoyyiigbdblmrjfx6dwbi44ee4p7747cvy)
