Would be awesome to have a browser extension that could create a bridge between ChatGPT and VSCode, applying Morph in between (or Claude instead of ChatGPT). Essentially use the web interface, instead of the APIs for agentic coding
Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
51–60 of 196 posts
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#52Earlier 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.
Have you tried any of the ludicrously fast LLM demos yet?
https://inference.cerebras.ai/ and https://groq.com/ and https://deepmind.google/models/gemini-diffusion/ (waitlisted) are all 10 to 100x faster than regular models, which really does have a meaningful impact on how I interact with them because I don't have to disengage for 15+ seconds while I wait for a response.
I have video demos of a few of those: https://simonwillison.net/2024/Oct/25/llm-cerebras/ and https://simonwillison.net/2024/Oct/31/cerebras-coder/ and https://simonwillison.net/2025/May/21/gemini-diffusion/
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#53Just for clarification here because I am a bit confused, Morph is a tool for integrating the output of other LLMs and not an LLM itself? It doesn't generate 4500 tok/sec, it can edit 4500 tok/sec?
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.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#541) Raw inference speed matters more than incremental accuracy gains for dev UX—agree or disagree?
Yeah, I love reviewing and debugging thousands of lines of buggy and dirty AI generated code. Who cannot love it?
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#55Earlier quoted context omitted.
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
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)
- polish what it generateRe: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#56Yeah sounds like exactly what we need
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#57Would be awesome to have a browser extension that could create a bridge between ChatGPT and VSCode, applying Morph in between (or Claude instead of ChatGPT). Essentially use the web interface, instead of the APIs for agentic coding
I think an MCP would do the job. We're shipping one out as we speak
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#581) Raw inference speed matters more than incremental accuracy gains for dev UX—agree or disagree? Yeah, I love reviewing and debugging thousands of lines of buggy and dirty AI generated code. Who cannot love it?
key word incremental - for fast apply to be useful it should be so fast and accurate that most people don't realize there's a model there at all
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#59Really like this. I've been trying microsoft's copilot and it's so clunky, particularly when applying edits. One would assume they have the resources to train the model..
Request: please provide a system prompt in the docs to help the llm generate the diff format that performs best w/ your models. LLMs frequently change the way they present diffs on upgrades and I don't want to be guessing which format is best.
EDIT: Please clarify your privacy policy. If my interpretation is correct, paying users will have their data retained and trained on? Is there any way to pay to use the service (w/o picking up the phone) and not have my data trained on?
4.1 Use of Service Data
Depending on your subscription tier:
Free Tier: We may use your submitted code data to train our models, improve our Services, and develop new features.
Engineer Tier: We may use your submitted code data to train our models, improve our Services, and develop new features, subject to the confidentiality provisions in your service agreement.
Enterprise Tier: We do not use your submitted code data for any purpose other than processing your immediate request. Your code data is never used for model training or service improvement.
Re: Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec
#60> 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 tasks. What about it is so difficult it could not be done with a smart diffing algorithm?