News for hackers. Stuff that matters.

alsima

alsima on Hacker News

Re:Show HN: A faster coding agent than Codex and Claude Code on Tuesday August 04, 2026 @03:45PM (#49173991)
You can also check out another demo here which compares Bullet speed to Codex/CC: https://youtu.be/rWVmG5fRKgE
Re:Show HN: A faster coding agent than Codex and Claude Code on Tuesday August 04, 2026 @03:44PM (#49173977)
Thanks sensho :)

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

Posted by alsima on Tuesday August 04, 2026 @03:33PM
from the show-hn dept.

https://www.codewithbullet.com

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...

( Read More... | 6 comments | 3 points | on HN )
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @11:21PM (#41177949)
Potentially true as well haha
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @06:22PM (#41176054)
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.
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @06:21PM (#41176038)
A lot...as you might imagine the costs of running the whole organization scale immensely.
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @05:38PM (#41175658)
It's the new cerebral valley slang dude
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @05:30PM (#41175592)
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.
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @05:14PM (#41175450)
Looking at Table 3: "Our [sampling and voting] method outperforms other methods used standalone in most cases and always enhances other methods across various tasks and LLMs", which benchmark did the majority vote algorithm perform worse in?
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @04:53PM (#41175246)
Hmmm I get what you mean...I think it's hard to sell a solution around this idea, but I think it will become something more like a common practice/performance improvement method. James Huckle on Linkedin (https://www.linkedin.com/feed/update/urn:li:activity:7214295...) mentioned that agent communication would be something more like a hyperparameter to tune which I agree with.
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @04:51PM (#41175219)
honestly agree. When I first started working with agents I didnt fully understand what it really was either but I eventually fell on a definition of an LLM call that performs a unique function proactively ¯\_(ツ)_/¯.
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @04:40PM (#41175089)
Well, you have Cognition AI and Devin that became a recent unicorn startup (partnerships with Microsoft and stuff) but true, I can't think of an agent that actually lives up to the hype (heard Devin wasn't great).
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @04:38PM (#41175061)
I would check out this company, Swarms (https://github.com/kyegomez/swarms) who's working with enterprises to integrate multi-agents. But definitely a great point to focus on, the research paper mentions that the scaling of performance reduces with complexity of the task, which is definitely true for SWE
Re:AI agents but they're working in big tech on Tuesday August 06, 2024 @03:48PM (#41174560)
If we structured AI agents like big tech org charts, which company structures would perform better? Inspired by James Huckle's thoughts on how organizational structures impact software design, I decided to put this to the test: https://bit.ly/ai-corp-agents.
Re:Show HN: Public and Free SWE-bench-lite evaluations on Tuesday July 16, 2024 @03:16AM (#40974265)
While I was working on building SIMA, a multi-agent software-engineer (which recently achieved 27.67% on SWE-bench-lite: https://www.swebench.com/), I realized that evaluations on the actual benchmark were quite inconsistent, resource-intensive, and computation heavy. That's why I built swebenchevals.com, a really easy hosted solution for anyone that is working with the SWE benchmark right now.