Hacker News: david_d8912

New comment by david_d8912 in "What I Actually Use Hermes and Obsidian For (Full Setup and Use Cases)"

david_d8912 — Sat, 23 May 2026 16:05:04 +0000

For curiosity: why Hermes? is there any part that you think it excels Claude or Codex (or it's just easier access from Telegram)

New comment by david_d8912 in "An obsidian plugin that answers the question: What's on your radar?"

david_d8912 — Wed, 20 May 2026 10:11:55 +0000

Interesting tool. A few suggestions with a quick glance: 1. can we make it representing daily real-time data by hook-up e.g. RSS, twitter? My personal use case is a "radar" would apply to more fresh info. The known tasks will be on a kanban (which also split priority or tag clearly)

2. not sure if it'll be better in-app, but quickly check the screenshot, the object titles are a bit small on radar view. It should be more readable.

New comment by david_d8912 in "3months ago, I predicted OpenClaw wouldn't uninstall cleanly and prepared for it"

david_d8912 — Mon, 18 May 2026 04:49:35 +0000

What's left over?

New comment by david_d8912 in "Ask HN: What LLM models are you using and why?"

david_d8912 — Sun, 17 May 2026 05:17:42 +0000

GPT-5.5 + Opus-4.7 here. Codex for pure coding task with clear goal, claude code for the rest. Also combined with opencode to experiment new models.

fyi: I didn't have much lock on Deepseek v4 pro, with opencode + openrouter it's incredibly slow. How did op did it?

New comment by david_d8912 in "Ask HN: Do you still spend time maintaining Claude.md / AGENTS.md files?"

david_d8912 — Sat, 16 May 2026 16:24:23 +0000

cool. I agree with all the front points. The last part ```Keep behavior instructions positive where possible```, do you have good experience on it. I'm only asking since my own experience is they're constantly not followed.

New comment by david_d8912 in "Ask HN: Do you still spend time maintaining Claude.md / AGENTS.md files?"

david_d8912 — Sat, 16 May 2026 16:00:29 +0000

The project directory, sure. I'm more of talking about behavior rules here. What are you guys writing, is it effective

Ask HN: Do you still spend time maintaining Claude.md / AGENTS.md files?

david_d8912 — Sat, 16 May 2026 14:33:18 +0000

For people using coding agents regularly: do you still invest time in user-level and repo-level instruction files like CLAUDE.md, AGENTS.md, etc.?

It's not a surprise that you don't expect the rules there to be followed even with less than 100 lines of changes. Yet still see folks like Karpathy post rules around with hundreds of stars.

Tell me if you're still spending the effort of trying claude.md, and are they effective, what're you writing in it.

Update: I'm more of talking about behavior rules here (coding standard, comment style, Do this and Don't do that, etc.). For facts like project directories, important doc ref, commands, sure that always helps.

Comments URL: https://news.ycombinator.com/item?id=48160604

Points: 9

# Comments: 10

New comment by david_d8912 in "Note-taking software,Novel ideas"

david_d8912 — Sat, 16 May 2026 14:25:29 +0000

It's already been the case for Obsidian? you create a github repo, create notes as md files, obsidian plugin sync it?

Actually not obsidian, but any note viewer like app. You put files in Google Drive or git repo for that matter.

New comment by david_d8912 in "How to improve code quality of Claude Code and codex (on 2026-05)"

david_d8912 — Thu, 07 May 2026 05:05:45 +0000

So it's a cli agent swarm? any difference to the omc, everything-cc swarm features

New comment by david_d8912 in "How to improve code quality of Claude Code and codex (on 2026-05)"

david_d8912 — Wed, 06 May 2026 13:16:45 +0000

Yeah that's what I'm doing, upfront work & code review. But it drastically slowing down the dev speed.

How to improve code quality of Claude Code and codex (on 2026-05)

david_d8912 — Wed, 06 May 2026 08:37:17 +0000

I'm using both claude code (opus-4.7) and codex (gpt-5.5). The agents are perfectly capable of delivering most features hands free these days, but the code quality is still miserable without another few rounds of prompt. And it's worse for personal vibe project without well-written history code files.

Simple example would be a poor extension of existing util methods, agent always duplicate and create new method instead of think about gracefully extending existing methods.

How are you guys solving this issue? A carefully maintained claude.md imo is only a mitigation, not a scalable solution.

Comments URL: https://news.ycombinator.com/item?id=48033774

Points: 2

# Comments: 4

New comment by david_d8912 in "Claude Code Routines"

david_d8912 — Wed, 15 Apr 2026 17:25:16 +0000

maybe a consequence of saving GPU for newer models? Also tuning effort level suppose to help, haven't get enough dp on this though

New comment by david_d8912 in "Google, Microsoft, Meta All Tracking You Even When You Opt Out"

david_d8912 — Tue, 14 Apr 2026 16:24:03 +0000

Now it'll be interesting to see if the AI companies do the same