Heard some insane rumors of the efficacy increase of this in action even though I don't know how you do it
Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
21–30 of 196 posts
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#22For anyone more curious about how this works, Fireworks wrote a blog post about it last year (I think):
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#23Earlier quoted context omitted.
I think it depends - the actual thing to measure it to keep a developer in flow state. Many errors as well as latency break this. To be brief yes, accuracy comes first. Quality is measured 2 main ways: 1) End-to-end: User query -> to task resolution. These are aider style benchmarks answering the question of actual task completion 2) Apply Quality: Syntax correctness, character diff, etc.. The error rate for large vs…
I don't believe anyone can be in some kind of "flow state" while waiting on LLM responses. I think it's funny that we complained for years about C and others being slow to compile and now folks are fine waiting seconds++ everytime they want to change something.
how so? Is your view that flow state at all isnt a thing, or just with using LLMs?
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#24Earlier quoted context omitted.
I don't believe anyone can be in some kind of "flow state" while waiting on LLM responses. I think it's funny that we complained for years about C and others being slow to compile and now folks are fine waiting seconds++ everytime they want to change something.
how so? Is your view that flow state at all isnt a thing, or just with using LLMs?
Flow state is 100% a thing, it's just impossible with LLMs (at least, for me). I can't be blocked waiting on things during a flow state or my mind starts wondering to other places.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#25Heard some insane rumors of the efficacy increase of this in action even though I don't know how you do it
the rumors are true! learn how we do it by joining the team :)
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#26> 1) Raw inference speed matters more than incremental accuracy gains for dev UX—agree or disagree? I know you are trying to generate some controversy/visibility, but i think if we are being transparent here, you know this is wrong. People prefer using larger (or reasoning) models, with much bigger diff in tok/sec just for quality in coding, it comes first. Even if i have a big edit to apply, like 5k tokens, 200-300m…
I think it depends - the actual thing to measure it to keep a developer in flow state. Many errors as well as latency break this. To be brief yes, accuracy comes first. Quality is measured 2 main ways: 1) End-to-end: User query -> to task resolution. These are aider style benchmarks answering the question of actual task completion 2) Apply Quality: Syntax correctness, character diff, etc.. The error rate for large vs…
> the actual thing to measure it to keep a developer in flow state.
Personally, I find flow state hard to achieve when I constantly have to switch modes to debugging LLM output or an edit error that I missed.
When the majority of time is spent waiting for the main LLM to think, I will always wait a few extra seconds for a better edit than risk having to spend multiple cycles playing find-the-bug because something didn't get applied correctly somewhere.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#27Earlier quoted context omitted.
how so? Is your view that flow state at all isnt a thing, or just with using LLMs?
Flow state is 100% a thing, it's just impossible with LLMs (at least, for me). I can't be blocked waiting on things during a flow state or my mind starts wondering to other places.
I've had the opposite experience.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#28Is there anyway to bring this into Claude Code?
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.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#29Earlier quoted context omitted.
how so? Is your view that flow state at all isnt a thing, or just with using LLMs?
Flow state is 100% a thing, it's just impossible with LLMs (at least, for me). I can't be blocked waiting on things during a flow state or my mind starts wondering to other places.
Fast Apply definitely helps with keeping flow state and is a large part of Cursor's success
Personally I work on multiple repos at a time to solve for this