Viewing profile — samatdav

cool! So the user does not need to use any additional tools?

Haha, yes it is a pattern. However, the claim here is that "our tiny model beats best model" is applicable for highly specific tasks.

Yes, you can download and host the fine-tuned open-source model like Llama. The fine-tuning is easy once you have the data, but gathering and cleaning data is challenging. There ar…

Thank you, we will!:) This was a quick landing page for us to start the conversation and gather feedback. We are trying to make sure we are not building something that nobody needs…

We used a single file for the context. It is a cherry-picked example, you are right. I wanted to demonstrate a simple visual change that our model did correctly unlike Sonnet-3.5. …

Good point, I agree, we haven't shared enough details. Since we are very early, we only got high level results and want to get feedback on what direction would be most applicable a…

I agree. Our local early results were promising were a higher percentage of code change requests produced a functionally correct output. We will post more metrics and data in the f…

Not yet, but we plan to publicly host a fine-tuned model so anyone can try.

We run a set of change requests on the discourse repo. Good point, we plan to publish more detailed testing benchmarks and metrics on the website.

Good point, we plan to publish more benchmarks and also publicly host a model for anyone to try. We think Llama is a good option but as we progress we will test other open source m…

Thank you! Will email you within a couple of days:)

Yes, we fine-tune for each codebase. Now we are focusing on larger enterprise codebases that would: 1. benefit from the fine-tuning the most. 2. have the budget to pay us for the s…

Thank you for the idea! We are also considering upsampling and distillation. But on high level, correctly setting up the data for simple fine-tuning can already produce great resul…

I agree, we plan to publish more benchmarks and metrics. We also want to publicly host our fine-tuned model for one of the open-source repos so that people can try themselves again…

Good point, we should provide more detailed metrics. Since we are very early, we focus on the main metric in our view: higher accuracy of changes to be more practically usable. We …

Thank you for the suggestion, we will take a look!

Looks like a great repo to try the fine-tuning! I will email you, thanks!

Could be done in the future. Our current focus is highest accuracy. But there are no limitations on the models - just would depend on user preference of size/performance tradeoff.

I agree, we need to post more data. Since we are very early (<1 month) we just shared the initial results. Discourse repo was just a good option since it is a big public repo that …

I understand the concern but we don't need anyone's IP. Unfortunately, it is hard to provide fine-tuning solution without access to the codebase. We just think that using a large g…

At Asana we did not do any fine-tuning because it was too complicated even for our AI org of 40 engineers. We believe we can do it by setting up and cleaning data correctly.

Good point! We are just very early and our experience is our main selling point. We plan to remove it.

Hi HN! I'm Samat, the co-founder from the video. Thank you for the critical feedback, great points. 0. Is this a scam? No. We're very early (started 1. Company logos. You're right.…

Hi! Currently we generate a whole diff (like cmd+shift+k in Cursor). But plan to add there rest soon!:)

Exciting - will give it a try!:)