Filippo Valsorda @filippo.abyssdomain.expert · 07/08/2026It’s very clear by now that if LLMs are not improving your software quality it’s either a revealed preference (yours or your org’s) for more volume vs more quality, or a skill issue. The level of testing and review they are enabling in the Go cryptography standard library is amazing. 935835
Michael Pyne @blindmansbinary.bsky.social · 26/08/2026I've even had fully local LLMs manage to give substantive, actionable feedback on stuff I've written. Not something to just uncritically let loose but it should absolutely help make your software better, especially with modern models. 000