2. Sometimes watching Claude do inline edits I cringe watching it delete almost the entire file line by line. I think when early in exploring a problem it's best to torch the previous version and fully re-write than to assume incremental.
Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
151–160 of 196 posts
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#152The most important question for any new company based around generative ML: how did you source training data, and did you observe the licesning (e.g., never use code under GPL or default copyright conditions)?
Very few companies can or are willing to answer that.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#153Impressive demo! Is there any rate limit (TPM)?
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#154It's more expensive than Gemini flash which can actually write pretty decent code (not just apply a diff). Fast AI edit application is definitely great but that's pretty expensive
Morph v3 fast: Input: $1.20 / M tokens, Output $2.70 / M tokens
Gemini 2.5 Flash: $0.30 / M tokens, Output $2.50 / M tokens
(Source: OpenRouter)
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#155How does this compare to relace, which I believe is also a YC company? They seem to have very similar functionality [0] [0] https://www.relace.ai/
Good question, they also list the same customers (create.xyz, continue.dev)
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#156Earlier quoted context omitted.
Fully agree. The very 1st thing you do after you get a proposed set of changes from an AI model is to review them carefully before applying them. Most of the time it duplicates code because it skipped specific tokens or context that was out of it's window and the user didn't include it in their prompt. Batch applying any changes is just a way to create even harded code to debug and accumulating such bulk code injecti…
if you've used cursor, you've probably felt how seamless fast apply can feel - fast apply is accurate and fast to the point where most don't even realize its a model
Absolutely, when stuff runs fast it's better UX compared to when the stuff runs slow.
I think what parent comments suggest is, the speed of applying a diff is not the major bottleneck in LLM-assisted coding, and improvements in other aspects are much more desirable (e.g. correctness, or even speed of thinking models themselves).
In a world where diff application is a real pain point, it's likely one of the last pain points in the field.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#157Earlier quoted context omitted.
Correct, but morph is a LLM as well. In practice its basically Big LLM using small LLM as a tool call
I see. How is this not going to get run over immediately by big players? Google's diffusion model is already in the wings, and it's both wicked fast and ~flash-lite intelligent.
Conventional tools are also a threat. Nothing about this problem is AI-specific.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#158Doesn’t Apple’s new model do the same thing? https://huggingface.co/apple/DiffuCoder-7B-cpGRPO
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#159Earlier quoted context omitted.
I do not use Opus for coding, I much prefer Sonnet. Many tasks work better with iteration/supervision and Sonnet makes that feasible.
yeah same. I feel like Opus tends to be slightly more sycophancy leaning on technical topics
Interesting. I use Opus exclusively (like $1000/day in tokens) via Claude Code. Do you really think Sonnet is better for programming? I’m not sure I agree, though I’d love to save $900/day by taking you up on it.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#160Earlier quoted context omitted.
Correct, but morph is a LLM as well. In practice its basically Big LLM using small LLM as a tool call
I see. How is this not going to get run over immediately by big players? Google's diffusion model is already in the wings, and it's both wicked fast and ~flash-lite intelligent.
You can run more intelligent traditional LLMs at higher speeds than the Google diffusion model. Even then, it runs nowhere near 4500tok/s, and such small models generally suck in terms of accuracy compared to a specialized, fine tuned one.