Hacker News: alsima

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 20:23:47 +0000

Thank you!

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 19:39:31 +0000

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.

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 19:30:30 +0000

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.

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 19:06:25 +0000

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.

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 18:58:56 +0000

I think that if there are many players in the space, it's a problem worth working on! Like I said in the post, our main problem is speed and that's what we're trying to fix. It's been a problem, and it still is a problem. We have tried tools like OpenCode, Pi, etc. but for our speed issue, it did not fix it. If we go down dying on this boat, so be it, at least we went down dying on a problem we care about!

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 18:54:29 +0000

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.

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 18:49:46 +0000

We're optimizing every day :)

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 18:47:56 +0000

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.

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 18:45:30 +0000

We'll get on that :)

New comment by alsima in "Launch HN: Bullet (YC S26) – A Faster Coding Agent"

alsima — Thu, 13 Aug 2026 10:48:35 +0000

Thanks for bringing this up and trying it out! We've disabled Cmd+Option+I in the new version and also have a message during signup about sharing chats with Bullet, let us know if you run into any other issues!

New comment by alsima in "Show HN: A faster coding agent than Codex and Claude Code"

alsima — Wed, 05 Aug 2026 07:54:18 +0000

Thanks for the detailed feedback, this was really valuable.

We fixed file autocomplete, automatic CLAUDE.md loading for Claude subscription sessions, and the plan issues. Plans now only appear when requested, and progress only updates after the related work has actually been done.

Your comparison with Claude Code is fair. Speed remains something we're trying to optimize outside of benchmarks, and long running tasks with plans seems to be something we need to improve. We're actively working on more optimization to latency and unnecessary model calls.

Thanks again for the comment and if you could try the latest build when you have time, would love to hear your thoughts again!

New comment by alsima in "Show HN: A faster coding agent than Codex and Claude Code"

alsima — Tue, 04 Aug 2026 19:45:24 +0000

You can also check out another demo here which compares Bullet speed to Codex/CC: https://youtu.be/rWVmG5fRKgE

New comment by alsima in "Show HN: A faster coding agent than Codex and Claude Code"

alsima — Tue, 04 Aug 2026 19:44:25 +0000

Thanks sensho :)

Show HN: A faster coding agent than Codex and Claude Code

alsima — Tue, 04 Aug 2026 19:33:34 +0000

Hi HN, excited to be sharing this with you guys today.

TL;DR: Bullet is a fast coding agent.

At our company, we were burning hours waiting on agent runs. The models weren’t the problem. The agent loops around them were slow (unnecessary planning, oversized context, repeated searches, and serial tool calls).

So we built Bullet as a passion project, the goal being to help you iterate faster, without giving up quality: - It automatically selects the model and reasoning level for each prompt. - It runs independent searches, reads, and commands in parallel. - It uses targeted code search instead of embedding the entire repository. - It works with your Claude Code or Codex subscription, OpenAI/Anthropic/xAI API keys, or an on-device model with no key.

Claude Code and Codex each center on their own model ecosystem. OpenCode gives you many models, but largely leaves model selection and configuration to you. Bullet sits above the models. Connect what you already pay for, then let Bullet choose the fastest path for every task.

On SWE-bench Verified, Bullet resolved 479/500 issues (95.8%, top 3 on the leaderboard) in one attempt, averaging 119 seconds per task (35–67% faster than mini-SWE-agent + Fable/Sol). Full results and methodology here: https://www.codewithbullet.com/blog/benchmark-results.html

We would love honest feedback on the product! It takes less than a minute to download and set up. We’d love to hear what you like about Bullet, and what sucks. The Mac app DMG release is on our website: https://www.codewithbullet.com/

P.S: we hid a code on the website, see if you can unlock the secret page at the footer (all built with Bullet) :) https://youtu.be/34wfiSoSw4Q

Comments URL: https://news.ycombinator.com/item?id=49173799

Points: 9

# Comments: 6

Anyone else think Claude Code and Codex are too slow? We hate it

alsima — Wed, 29 Jul 2026 20:12:19 +0000

Article URL: https://bullet.davidhf.com

Comments URL: https://news.ycombinator.com/item?id=49102406

Points: 4

# Comments: 0

New comment by alsima in "AI agents but they're working in big tech"

alsima — Wed, 07 Aug 2024 03:21:03 +0000

Potentially true as well haha

New comment by alsima in "AI agents but they're working in big tech"

alsima — Tue, 06 Aug 2024 22:22:30 +0000

Definitely not saying multi-agents is all you need for SWE-bench haha. I touch on this at the end of the blog post, where I mention jumps in progress require better base models or tooling.

New comment by alsima in "AI agents but they're working in big tech"

alsima — Tue, 06 Aug 2024 22:21:04 +0000

A lot...as you might imagine the costs of running the whole organization scale immensely.

New comment by alsima in "AI agents but they're working in big tech"

alsima — Tue, 06 Aug 2024 21:38:16 +0000

It's the new cerebral valley slang dude

New comment by alsima in "AI agents but they're working in big tech"

alsima — Tue, 06 Aug 2024 21:30:42 +0000

I see. Agree with the point about marginal improvements at a hefty increase in computational cost (I touch on this a bit at the end of the blog post where I mention that better performance requires better tooling/base models). Though I would still consider sampling and voting a “multi-agent” framework as it’s still performing an aggregation over multiple results.