Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Bullet (YC S26) – A Faster Coding Agent

codewithbullet.com

Post reply on HN
Print view View original

31–40 of 93 posts

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#31

Post by alsima »

esafak wrote: post #24

I think this adds no value. I would stick to OpenCode. Things I would value: high-fidelity visualization (bonus points for Figma-like visual edits), good tool use (don't force me to tell the model), token efficiency, resource efficiency. Things that are not problems: * Routing: OpenCode predefines subagents that you can set to appropriate models. * Search: there are AST and embedding-based search MCPs. I use https://…

Thanks for the feedback, we do focus on good tool management, context efficiency, etc. As for routing, ideally it isn't the user who has to route themselves, but a layer that routes for them.

Thanks for the link to the repo! We have looked at things like https://github.com/Graphify-Labs/graphify but haven't had a chance to rigorously evaluate their speed boosts on our harness.

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#32

Post by seizethecheese »

alsima wrote: post #26
seizethecheese wrote: post #20

Earlier quoted context omitted.

I did read "Full results and methodology". It doesn't seem to show which agents you are routing to. Am I missing something? And how do those agents score on SWE-Bench Verified?

The benchmark wasn't evaluated with the router, we wanted an apples-to-apples comparison of our harness against other harnesses like mini-swe-agent on the same models to see if we added speed + cost value beyond routing.

Okay, that makes more sense, but then this post is very confusing. Why mention the router at all? Or does your live system have a router and the eval doesn't? In which case why not publish an eval with the router?

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#33

Post by seizethecheese »

alsima wrote: post #29
seizethecheese wrote: post #17

Earlier quoted context omitted.

The same thing holds for speed. I could build a system that speeds up Fable on GPQA Diamond ~50%, while improving score, by literally randomly selecting between Fable and Gemini 3.7 Flash. (Solve time for Flash is 0.1min and 0.8min for Fable, with Flash having a better score.) Hell, I could publish better score at 87.5% time reduction by having the router always pick Flash!

Like I mentioned, we omitted routing from the benchmark and evaluated with our strongest model modality. Also, randomly selecting between Fable and Gemini 3.7 Flash wouldn't preserve quality.

Mentioned where?

What do you mean it wouldn't preserve quality? I demonstrate in the comments here how it would on a saturated benchmark.

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#34

Post by alsima »

seizethecheese wrote: post #32
alsima wrote: post #26

Earlier quoted context omitted.

The benchmark wasn't evaluated with the router, we wanted an apples-to-apples comparison of our harness against other harnesses like mini-swe-agent on the same models to see if we added speed + cost value beyond routing.

Okay, that makes more sense, but then this post is very confusing. Why mention the router at all? Or does your live system have a router and the eval doesn't? In which case why not publish an eval with the router?

Fair point, yes, the router is only in the live system (we'll try to make that more clear). We thought that comparing the router to other harnesses on the benchmark wouldn't be a fair evaluation because the speed/cost gains from our harness would mostly be from using cheaper and simpler models rather than actually having a better harness.

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#35

Post by alsima »

seizethecheese wrote: post #33
alsima wrote: post #29

Earlier quoted context omitted.

Like I mentioned, we omitted routing from the benchmark and evaluated with our strongest model modality. Also, randomly selecting between Fable and Gemini 3.7 Flash wouldn't preserve quality.

Mentioned where? What do you mean it wouldn't preserve quality? I demonstrate in the comments here how it would on a saturated benchmark.

Mentioned in my comment above. Sorry, I thought you were talking about Gemini 3.6 Flash, not their new one. Yes, that's the reason why we didn't include the router in the benchmark to have a fair comparison of the harness itself.

Re: Launch HN: Bullet (YC S26) – A Faster Coding Agent

#38

Post by tomhow »

docheinestages wrote: post #14
tontinton wrote: post #9

Are you freaking kidding me with YC throwing money at something like this? I guess I can fund raise just by having built https://maki.sh , and months ahead of other founders too...

YCombinator's investments are unfortunately very questionable nowadays.

People were saying that about YC in 2009, when Airbnb and Stripe were funded. YC’s philosophy has always been to invest in a great many companies, accepting that you can’t know in advance which will succeed, most will fail, but the ones that succeed will be successful enough to pay for all the losses.
Post reply on HN