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

71–80 of 196 posts

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

#71

Post by klank »

bhaktatejas922 wrote: post #65
klank wrote: post #50

Earlier quoted context omitted.

Time really is a flat circle. My software career started with me archaically flipping characters in a file I vaguely understood with long pauses waiting on magic compilers to give me my actual output. Now it's dying in the same place. Thankfully I got to spend the brunt of my career working through the fun, intermediate years.

I've never had so much fun coding in my life - you should definitely give it a try again!

Thanks, I appreciate the good vibes.

However, it's kind of a trope for me at this point that people assume a negative opinion of using generative AI in the development process is due to a lack of experience using it.

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

#72

Post by k__ »

deepdarkforest wrote: post #9

> 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 have to admit, that using slow models is unbearable when I used fast one before.

I don't know if the quality and speed are linearly related, though.

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

#73

Post by paulddraper »

deepdarkforest wrote: post #9

> 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 do not use Opus for coding, I much prefer Sonnet.

Many tasks work better with iteration/supervision and Sonnet makes that feasible.

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

#74

Post by AirMax98 »

k__ wrote: post #72
deepdarkforest wrote: post #9

> 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 have to admit, that using slow models is unbearable when I used fast one before. I don't know if the quality and speed are linearly related, though.

Seriously agree — try using something like Sonnet 3.7 and then switching to Gemini 2.5 Pro. The code that both output is fine enough — especially given that I mostly use LLMs as a fancy autocomplete. Generally a better prompt is going to get me closer to what I want than a more robust model. The speed hit with Gemini 2.5 Pro is just too substantial for me to use it as a daily driver.

I imagine the speed difference might not matter so much if you are performing seismic updates across a codebase though.

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

#75

Post by bhaktatejas922 »

Workaccount2 wrote: post #53
bhaktatejas922 wrote: post #46

Earlier 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 could make the argument about any startup really. To me its the same reason they don't build the foundational model for legal, for sales, etc.. - everything comes at a cost. Allocating researcher time to this is attention not spent on the general frontier model - losing 1-2% there is the difference of billions of dollars for them

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

#76

Post by deepdarkforest »

Cort3z wrote: post #60
deepdarkforest wrote: post #9

> 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…

As far as i understand, this is not +-300ms. It is 300ms vs. 10 sec or something. That is a huge difference. I personally find the time to wait for these larger models a limiting factor. It’s also probably a resource waste for fairly simple task like this. (Compared to the general function approximation of the llms) But I honestly feel like the task of smartly applying edits falls somewhat within traditional coding t…

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

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

#77

Post by walthamstow »

ashwindharne wrote: post #31
deepdarkforest wrote: post #9

> 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 do find that having inference happen ~50% faster is much more valuable to my workflow than a single digit accuracy increase. If I'm going to have to check that the changes are correct anyways, getting more iterations in faster feels much better than incremental accuracy. There's definitely a tipping point though. If the accuracy gains are so high that I can check its work less carefully or less often, the benefits…

Agreed. Sonnet 4 is supposedly better than Sonnet 3.5, but in Cursor 3.5 is much faster so that's what I use

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

#78

Post by bhaktatejas922 »

paulddraper wrote: post #73
deepdarkforest wrote: post #9

> 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 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

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

#79

Post by bhaktatejas922 »

Cort3z wrote: post #60
deepdarkforest wrote: post #9

> 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…

As far as i understand, this is not +-300ms. It is 300ms vs. 10 sec or something. That is a huge difference. I personally find the time to wait for these larger models a limiting factor. It’s also probably a resource waste for fairly simple task like this. (Compared to the general function approximation of the llms) But I honestly feel like the task of smartly applying edits falls somewhat within traditional coding t…

it's a bit unclear why a model works best here. in short - smart diffing is edge case hell and you'll never capture all of them

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

#80

Post by bhaktatejas922 »

0x457 wrote: post #55
bhaktatejas922 wrote: post #29

Earlier quoted context omitted.

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

I do it like simultaneous exhibition in chess: - Multiple repos or independent changes in monorepo - First round of changes idgaf about anything beyond public interface and unit tests - I review public interface and make changes if needed - I review unit tests it wrote to see that at least from the outside it looks alright. - here I either: - make more unit tests (features, edge cases and make it write code for it) -…

sounds like flow state to me
Post reply on HN