Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

91–100 of 196 posts

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

#92

Post by bhaktatejas922 »

Cort3z wrote: post #88
deepdarkforest wrote: post #76

Earlier quoted context omitted.

you misunderstood. its 300ms just for the apply model, the model that takes your coding models output (eg sonnet) and figures out where the code should be changed in the file. Cursor has its own, and claude uses a different technique with strings as well. So its 10sec vs 10sec +300ms using your analogy

Their selling point is to be a more open version of what cursor has. So the alternative is to use a full llm. So it is 10s+ 10s vs 10s+ 300ms

yep!

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

#93

Post by bravesoul2 »

bhaktatejas922 wrote: post #92
Cort3z wrote: post #88

Earlier quoted context omitted.

Their selling point is to be a more open version of what cursor has. So the alternative is to use a full llm. So it is 10s+ 10s vs 10s+ 300ms

yep!

For someone not heavy in this space. I use GH copilot at work. I might switch to cursor. I am not into the details of the tools just care does it help me or not. For us it might be worth having an easier to understand value proposition.

It may take a bit if explaining and that's OK. But the big question is as someone doing my enterprise microservice who isn't heavy into AI why do I switch to you.

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

#94

Post by golergka »

I don't think this makes any sense as a standalone product, but I wish I had it in my claude code and aider as an intermediate step right away. The latter tool, while less popular, already supports _exactly_ this workflow in the architect mode — a good candidate to be your first integration, I think.

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

#96

Post by SatvikBeri »

bhaktatejas922 wrote: post #35
halfjoking wrote: post #28

Earlier quoted context omitted.

Make an MCP server, and turn off the Write|Edit|MultiEdit tools? Actually - that's what this company should do. It should be an MCP server so anyone could plug it into any agent with a url and an API key.

great idea! we'll have one up soon :)

Can you set up a mailing list or something where we can keep up with updates? I'm interested in trying this as soon as it works with Claude Code.

Edit: I'd be particularly interested if there's a way to run a sort of comparison mode for a while, so I can get a sense of how much accuracy I'm losing, if any. Even at the cost of initial performance.

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

#98

Post by 0x457 »

bhaktatejas922 wrote: post #89
0x457 wrote: post #82

Earlier quoted context omitted.

oh it's fore sure is. But I use amazon q almost exclusively. One thing that gets me out of this state: when I have to do the math on "should I just do it myself" vs "keep refining prompt/context until this thing finally gets it right".

so frustrating how slow edits are in Q dev

Sometimes it splits edits to a single file into way to many fs_write(s) and often get stuck not being able to apply edits. It also so conservative with using your machine resources: kept trying to run test suit with a single worker, like come on, I paid for 32 cores, I will be using 32 cores.

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

#100

Post by joshmlewis »

I'm going to test implementing this for my project https://promptslice.com and see how it does with text based edits. I assume it will do ok.

I'm also really curious about the XML tool calls in the documentation. I have not heard of this being the norm for tools like Cursor. Is that still the case? I feel like I'm pretty in the know about this stuff but must have missed that trend.

Post reply on HN