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

171–180 of 196 posts

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

#171

Post by handfuloflight »

klank wrote: post #144
handfuloflight wrote: post #107

Earlier quoted context omitted.

Well you could articulate what issues you have with it. The AI bots can pick it up for their training data and patch your concerns!

> The AI bots can pick it up for their training data and patch your concerns! This is borderline mystical AI speak to me. I know what you mean, and no, it doesn't work like that. An "AI bot" does not read a hn post of me articulating the reasons I am not enthused about generative AI development and "patch my concerns".

Next time, I'll wrap it up in .

Truly ironic the AI readily detected what I said as sarcastic. Without context. https://claude.ai/share/7d14287d-c066-4927-8942-8eb8dd8d7e7f

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

#172

Post by klank »

handfuloflight wrote: post #171
klank wrote: post #144

Earlier quoted context omitted.

> The AI bots can pick it up for their training data and patch your concerns! This is borderline mystical AI speak to me. I know what you mean, and no, it doesn't work like that. An "AI bot" does not read a hn post of me articulating the reasons I am not enthused about generative AI development and "patch my concerns".

Next time, I'll wrap it up in . Truly ironic the AI readily detected what I said as sarcastic. Without context. https://claude.ai/share/7d14287d-c066-4927-8942-8eb8dd8d7e7f

Ah, thanks for the explination. I actually was confused a bit. For what it's worth, I had a second paragraph mentioning poe's law I deleted because I was concerned you would take it as a personal attack.

I should have left it in, knowing you were sarcastic I think you'd have appreciated me being confused about whether you were being satirical or not.

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

#173

Post by conartist6 »

thegeomaster wrote: post #164
conartist6 wrote: post #162

Earlier quoted context omitted.

Context awareness, yep. Response to fuzzy inputs... idunno, why does it need that? The thing I think is really silly is that it tries to make incremental writes to a flat file really fast, which is an impossible goal. As the file gets bigger your writes will just get slower and slower and slower at a rate that increases linearly with the size of the file.

LLMs will generate unpredictable, very humanlike code edits in this form. They might use comments like "same function as above", "rest of the function with similar changes", "function ABC is no longer needed", "function ABC same as above", etc. Your code edit model must resolve all of these, or flag an error in case of too much ambiguity. I would think a classical algorithm would have a lot of trouble differentiating…

I agree that sorting something that messy can't easily be done with a heuristic expert system, but I'm registering my concern that the whole approach is predicated on first making a huge mess with one LLM then cleaning up the mess with another.

The classical approach is more like "change the definition of the problem until you don't need to make a big mess in the first place"

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

#174

Post by bhaktatejas922 »

throwaway2037 wrote: post #163
candiddevmike wrote: post #18

Earlier 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.

> we complained for years about C and others being slow to compile For C? I don't remember that, unless headers are poorly managed. C++? Definitely yes.

What do we not complain about if we're being honest?

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

#175

Post by bhaktatejas922 »

handfuloflight wrote: post #171
klank wrote: post #144

Earlier quoted context omitted.

> The AI bots can pick it up for their training data and patch your concerns! This is borderline mystical AI speak to me. I know what you mean, and no, it doesn't work like that. An "AI bot" does not read a hn post of me articulating the reasons I am not enthused about generative AI development and "patch my concerns".

Next time, I'll wrap it up in . Truly ironic the AI readily detected what I said as sarcastic. Without context. https://claude.ai/share/7d14287d-c066-4927-8942-8eb8dd8d7e7f

the claude link is hilarious, hahaha

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

#176

Post by bhaktatejas922 »

Kamshak wrote: post #154

It'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)

Thats for 0 data retention - on the Morph website its: 0.80 /1M token input, $1.20 /1M token output. We have discounts for large volumes/reserved instances as well

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

#177

Post by bhaktatejas922 »

thegeomaster wrote: post #164
conartist6 wrote: post #162

Earlier quoted context omitted.

Context awareness, yep. Response to fuzzy inputs... idunno, why does it need that? The thing I think is really silly is that it tries to make incremental writes to a flat file really fast, which is an impossible goal. As the file gets bigger your writes will just get slower and slower and slower at a rate that increases linearly with the size of the file.

LLMs will generate unpredictable, very humanlike code edits in this form. They might use comments like "same function as above", "rest of the function with similar changes", "function ABC is no longer needed", "function ABC same as above", etc. Your code edit model must resolve all of these, or flag an error in case of too much ambiguity. I would think a classical algorithm would have a lot of trouble differentiating…

precisely. we work well on files up to 2k lines. It's hard to wrap your head around at first, but code merge has 100s of edge cases to deal with. Its the perfect application for a model

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

#178

Post by bhaktatejas922 »

agrippanux wrote: post #167

How does this compare to Google Diffusion? Diffusion writes out at seemingly the speed of thought.

we're quite a bit faster and specifically training for merging code edits.

Google diffusion is a swing at a generalist model. Super cool work nonetheless

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

#179

Post by bhaktatejas922 »

helsinki wrote: post #158

Doesn’t Apple’s new model do the same thing? https://huggingface.co/apple/DiffuCoder-7B-cpGRPO

This is a coding model, not a code merge model. What we do is 1 thing, extremely well - merging code edits into original files
Post reply on HN