fry69 @fry69.dev · 31/05/2026I agree that in the age of LLMs the quality bar should get raised. It is too easy to produce low quality and very verbose code. Quality vetting by humans should be mandatory factors now, also terseness should be encouraged. 130
fry69 @fry69.dev · 31/05/2026Overly verbose PR descriptions without a clear summary are already a red flag for me. I stop reading those and ignore them if I do not get what they are about after one or two paragraphs. 210
fry69 @fry69.dev · 31/05/2026LLMs are not speed booster for (serious) coding. They are quality booster if used correctly. LLMs also allow fast prototyping, but that is a completely different story. Relevant in this context -> simonwillison.net/2026/May/31/... @simonwillison.net has a positive take on this.simonwillison.netThe solution might be cancelling my AI subscriptionI find this post by David Wilson very relatable. David lists 16+ projects he's spun up with AI tooling, and concludes: I didn't mean to build most of these things. … 031
jfc @jfc.ninja · 01/06/2026my current stance on using LLMs for writing is, "I should not be able to tell in the final draft that an LLM was involved" 110
