Hacker News: muratsu

New comment by muratsu in "Cursor 3"

muratsu — Fri, 03 Apr 2026 02:08:54 +0000

I find it interesting that you are on the enterprise plan and are not default willing to pay more for more intelligence. Most people I know who are on the enterprise plan are wishing there existed a 2x intelligent model with 2x price.

New comment by muratsu in "Show HN: Cq – Stack Overflow for AI coding agents"

muratsu — Wed, 25 Mar 2026 21:32:56 +0000

I’m sure there will be more elegant solutions in the future but putting everything in md files under a docs folder is a start.

New comment by muratsu in "Show HN: Cq – Stack Overflow for AI coding agents"

muratsu — Tue, 24 Mar 2026 00:23:02 +0000

The problem I'm having with agents is not the lack of a knowledge base. It's having agents follow them reliably.

New comment by muratsu in "Pi – A minimal terminal coding harness"

muratsu — Tue, 24 Feb 2026 23:53:45 +0000

I’m working with a friend to build an ui around Pi to make it more user friendly for people who prefer to work with a gui (ala conductor). You can check out the repo: https://github.com/philipp-spiess/modern

New comment by muratsu in "Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue"

muratsu — Mon, 16 Feb 2026 23:42:28 +0000

For those using something like this daily, what key combinations do you use to record and cancel. I’m using my capslock right now but was curious about others

Ask HN: How to go back to listening to MP3s?

muratsu — Sat, 27 Dec 2025 22:58:34 +0000

I have been a paying Spotify customer for many years now. Thanks to the yearly wrapped event, I am reminded how my use pattern is listening to a limited amount of tracks on repeat.

I'm curious if any of you has made the switch back to listening to mp3s? If you did, which apps are you using?

Comments URL: https://news.ycombinator.com/item?id=46406311

Points: 19

# Comments: 60

New comment by muratsu in "Migrating the main Zig repository from GitHub to Codeberg"

muratsu — Thu, 27 Nov 2025 03:01:20 +0000

> Putting aside GitHub’s relationship with ICE, it’s abundantly clear that the talented folks who used to work on the product have moved on to bigger and better things, with the remaining losers eager to inflict some kind of bloated, buggy JavaScript framework on us in the name of progress.

This says more about the author than anything else.

New comment by muratsu in "Adk-go: code-first Go toolkit for building, evaluating, and deploying AI agents"

muratsu — Wed, 12 Nov 2025 07:51:55 +0000

fwiw it says it is gemini optimized on readme. Unsure to what extent

New comment by muratsu in "New gel restores dental enamel and could revolutionise tooth repair"

muratsu — Wed, 05 Nov 2025 19:58:50 +0000

Wait what? Please share

New comment by muratsu in "Zed's Pricing Has Changed: LLM Usage Is Now Token-Based"

muratsu — Wed, 24 Sep 2025 17:31:37 +0000

For those of us building agentic tools that require similar pricing, how does one implement it? OpenRouter seems good for the MVP, but I'm curious if there are alternatives down the line.

New comment by muratsu in "How to use Claude Code subagents to parallelize development"

muratsu — Sat, 13 Sep 2025 09:39:56 +0000

Why not just use only async agents? You can fire off many tasks and check PRs locally when they complete the work. (I also work on devfleet.ai to improve this experience, any feedback is appreciated)

New comment by muratsu in "I ditched Spotify and set up my own music stack"

muratsu — Thu, 04 Sep 2025 23:35:33 +0000

Going through the trouble of maintaining a home server is not worth it for me. I wish dropbox offered some extra service for music/video.

New comment by muratsu in "Parallel AI agents are a game changer"

muratsu — Wed, 03 Sep 2025 00:12:45 +0000

The codex model is trained differently than the normal models. It has extra training on how to use cli and I find it to be better at project scope tasks (eg running tests, migrations, etc). Whereas in my experience Claude is the better coding model.

New comment by muratsu in "Parallel AI agents are a game changer"

muratsu — Tue, 02 Sep 2025 23:56:17 +0000

I find Codex and Claude Code to have different strength/weaknesses and wanted to be able to use them from a single interface. Currently hacking on https://devfleet.ai to make agent management more easy on myself.

Briefly mentioned on the article but async agents really thrive on small and scoped issues. Imagine hooking them up to your feedback tool (eg canny) and automatically having a PR as you review the customer feedback. Now this would likely not work for large asks but for smaller asks, you can just accept the PR and ship it really fast!

New comment by muratsu in "Launch HN: Dedalus Labs (YC S25) – Vercel for Agents"

muratsu — Thu, 28 Aug 2025 18:15:47 +0000

Oh interesting. I've previously looked into implementing it myself but seemed like it would require a lot of effort. I would love to connect and learn more about your implementation. What's the best way to reach out to you? My email is available on my profile.

New comment by muratsu in "Launch HN: Dedalus Labs (YC S25) – Vercel for Agents"

muratsu — Thu, 28 Aug 2025 17:37:07 +0000

Congrats on the launch. I see that you're charging 5% on Balance Reloads. This pricing model seems to be getting popular across multi-LLM applications. Was curious to know how did you go about implementing it? or are you just passing on the 5% of openrouter

Coding from Your Phone

muratsu — Tue, 19 Aug 2025 18:40:42 +0000

Article URL: https://www.devfleet.ai/blog/coding-from-your-phone

Comments URL: https://news.ycombinator.com/item?id=44954808

Points: 3

# Comments: 0

New comment by muratsu in "Teaching GPT-5 to Use a Computer"

muratsu — Mon, 18 Aug 2025 02:41:24 +0000

For someone who wants to do “archon‑mini is a 7B Qwen‑2.5‑VL–based executor (dynamic‑res ViT) fine‑tuned with GRPO for GUI grounding” part at home, is there a guide/post you would recommend?

New comment by muratsu in "Claudia – Desktop companion for Claude code"

muratsu — Sun, 17 Aug 2025 22:30:31 +0000

I’ve recently built something which runs helps you run cc in cloud sandboxes maybe that would be helpful: https://www.devfleet.ai

Reflections on the React Community

muratsu — Mon, 11 Aug 2025 09:39:02 +0000

Article URL: https://leerob.com/reflections

Comments URL: https://news.ycombinator.com/item?id=44862400

Points: 8

# Comments: 0