News for hackers. Stuff that matters.

A comment on Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec. Parent comment

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by johnfn on Monday July 07, 2025 @01:19PM (#44492532)
Anyone can get 10 tok/sec - just tell the model to output the entire file with changes, rather than just the delta.

Whatever LLM you're using will have a baseline error rate a lot higher than 2%, so you're going to be reviewing all the code it outputs regardless.

[ Parent | on HN ]
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bhaktatejas922 on Monday July 07, 2025 @03:11PM (#44493672)
yeah even claude is well over 11% error rates with search and replace
[ Parent | on HN ]