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

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bigyabai on Monday July 07, 2025 @12:07PM (#44491767)

The marketing language seems to suggest they're insecure over quality and want to promote quantity. But I'm in the same boat as you - I would happily take 10 tok/sec of a correct answer instead of wasting an hour curating 4500 tok/sec throwaway answers. Benchmark performance matters 100x more than your latency.

If these "hot takes" extend into Morph's own development philosophy, then I can be glad to not be a user.

[ Parent | on HN ]

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bhaktatejas922 on Monday July 07, 2025 @12:18PM (#44491874)

There's no amount of error rate that's acceptable to us - edits should always be correct. We've just found anecdotally the saving users time is just provably also very important for churn, retention and keeping developer flow state, right after accuracy.

[ Parent | on HN ]

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bigyabai on Monday July 07, 2025 @12:22PM (#44491924)

Then why are you using a custom model instead of an industry-leading option?

I don't mean to be rude, but I can't imagine you're selling a product on-par with Claude 3.7. Some level of performance tradeoff has to be acceptable if you prioritize latency this hard.

[ Parent | on HN ]

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bhaktatejas922 on Monday July 07, 2025 @12:26PM (#44491963)

We're not - our model doesn't actually think up the code changes. Claude-4 or Gemini still writes the code, we're just the engine that merges it into the original file.

Our whole thesis is that Claude and Gemini are extremely good at reasoning/coding - so you should let them do that, and pass it to Morph Fast Apply to merge changes in.

[ Parent | on HN ]

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 ]

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by IanCal on Monday July 07, 2025 @02:39PM (#44493385)

This is a code editing model. 10 tokens per second editing may as well not exist for any interactive use case.

[ Parent | on HN ]