Hacker News: andreagrandi

New comment by andreagrandi in "Sshole"

andreagrandi — Thu, 05 Nov 2026 14:47:17 +0000

This is fine :)

How I use Claude Code subagents to make my Claude Pro limits last longer

andreagrandi — Wed, 07 Oct 2026 22:04:49 +0000

Article URL: https://www.andreagrandi.it/posts/claude-code-subagents-to-save-usage/

Comments URL: https://news.ycombinator.com/item?id=49999407

Points: 2

# Comments: 0

Codex Weekly Limits Are Draining Way Too Fast – Is This a Bug?

andreagrandi — Mon, 17 Aug 2026 15:42:20 +0000

Article URL: https://community.openai.com/t/codex-weekly-limits-are-draining-way-too-fast-is-this-a-bug/1390408

Comments URL: https://news.ycombinator.com/item?id=49332837

Points: 4

# Comments: 0

New comment by andreagrandi in "Why Book Corners won't sync contributions back to OpenStreetMap"

andreagrandi — Mon, 03 Aug 2026 13:05:41 +0000

I haven't. That would be a completely different app which I'm not interested in working on, I'm afraid.

New comment by andreagrandi in "Why Book Corners won't sync contributions back to OpenStreetMap"

andreagrandi — Mon, 03 Aug 2026 08:08:47 +0000

> Maybe that part of the article needs further editing?

Yes, I should edit it. I had not though about the bulk download until another user on Mastodon suggested it to me.

> Also, if the data of your tool is now available under ODbL, then the tasks related to importing it into OSM can be effectively performed by anyone, not necessarily you.

Definitely. I would be more than glad if libraries which are not on OSM were added back, I just don't have the required spare time to go through all the process and also maintain it.

New comment by andreagrandi in "Why Book Corners won't sync contributions back to OpenStreetMap"

andreagrandi — Mon, 03 Aug 2026 07:55:45 +0000

Hello folks, author of Book Corners here. I just made the whole libraries db available for download (it's OBDL licensed).

It's available from every users dashboard (it's a ~2 MB compressed GeoJSON file). It includes both libraries orignally imported from OSM and additional libraries added by users.

While I still think the whole OSM process to submit back is a bit too much for the time I have available (but I still understand and respect), at least I want to give users an additional option to retrieve the data (in addition to the public API).

If you have any other advices, I will be glad to hear them and, compatibly with my spare time, I will try to implement them (if they make sense and are useful for users) :)

Thanks

New comment by andreagrandi in "Codex Security"

andreagrandi — Wed, 29 Jul 2026 08:29:00 +0000

Folks, are you SERIOUS?!

codex-security scan . [00:00] Preparing scan [00:00] Authentication: stored Codex credentials. [00:01] Preparing scan [31:25] Running scan codex-security: This content was flagged for possible cybersecurity risk. If this seems wrong, try rephrasing your request. To get authorized for security work, join the Trusted Access for Cyber program: https://chatgpt.com/cyber

I mean... wasn't this the intended goal? And you wasted all my tokens for nothing?!

Show HN: Meeting Notes Sync – import transcripts and AI summaries into Obsidian

andreagrandi — Thu, 18 Jun 2026 08:34:11 +0000

Article URL: https://community.obsidian.md/plugins/meeting-notes-sync

Comments URL: https://news.ycombinator.com/item?id=48582509

Points: 1

# Comments: 1

Why add an agent skill to a CLI that has a context command?

andreagrandi — Sun, 07 Jun 2026 21:05:41 +0000

Article URL: https://www.andreagrandi.it/posts/why-add-agent-skill-cli-context-command/

Comments URL: https://news.ycombinator.com/item?id=48438537

Points: 2

# Comments: 1

New comment by andreagrandi in "Anthropic takes legal action against OpenCode"

andreagrandi — Thu, 19 Mar 2026 21:22:22 +0000

You mean their tool (I use it daily) is so bad despite all the data they collect?

New comment by andreagrandi in "Show HN: Claude Code skills that build complete Godot games"

andreagrandi — Tue, 17 Mar 2026 07:52:45 +0000

And it's exactly what I was trying to do manually :D I accept the limit and say that probably doing a video game is not for me, but it's nice that a solution exists.

New comment by andreagrandi in "Show HN: Claude Code skills that build complete Godot games"

andreagrandi — Mon, 16 Mar 2026 20:10:36 +0000

Context: I've been using agents (both Claude Code and Codex) for my daily work and for personal projects, but always in domains where I had some knowledge and I'm currently happy with them.

I tried using Claude Code to build an RPG game with Godot and GDScript, using free to use assets: a total failure :/

The game was supposed to be many implementation steps long but I asked Claude to first produce a one area demo, so I could test the assets and choose the one I liked. First it produced some garbage using the assets randomly. Then it tried to copy from an existing demo but it had not idea where a door or a path were and at a certain point it even admitted it with something like: "I can't design an usable and nice area: I either make it functional and ugly or I copy and adapt the existing demo but I will have no clue about what is what"

I've never even attempted to develop games before so I'm sure I don't even know the basic concepts, but this use case definitely didn't work for me.

Maybe it could generate the code of the game if I provided the full design?

Show HN: Mb-CLI – CLI for Metabase. Designed for humans and AI coding agents

andreagrandi — Sat, 07 Mar 2026 06:41:18 +0000

Article URL: https://github.com/andreagrandi/mb-cli

Comments URL: https://news.ycombinator.com/item?id=47285094

Points: 3

# Comments: 0

New comment by andreagrandi in "Show HN: Claude-replay – A video-like player for Claude Code sessions"

andreagrandi — Fri, 06 Mar 2026 22:16:43 +0000

Question: how can you find the exact session you are looking for, among hundreds of them? I had a look at my ~/.claude/projects/*/ and I couldn't even find my last session.

New comment by andreagrandi in "Elevated Errors in Claude.ai"

andreagrandi — Tue, 03 Mar 2026 07:12:02 +0000

I must have missed something: why are people moving from OpenAI? Since they released gpt-5.3-codex I'be been using it and claude with opus-4.6 and Codex has always been better, more accurate, less prone to allucinations. I can do more with a 20$ OpenAI pland than with a Claude Max 100

Show HN: Book Corners – A map to discover and share free little libraries nearby

andreagrandi — Sat, 28 Feb 2026 15:55:48 +0000

Article URL: https://www.bookcorners.org

Comments URL: https://news.ycombinator.com/item?id=47196815

Points: 4

# Comments: 0

New comment by andreagrandi in "Anthropic officially bans using subscription auth for third party use"

andreagrandi — Thu, 19 Feb 2026 14:51:17 +0000

I haven't experiences this with gpt-5.3-codex (xhigh) for example. Opus/Sonnet usually work well when just released, then they degrade quite regularly. I know the prompts are not the same every day or even across the day, but if the type of problems are always the same (at least in my case) and a model starts doing stupid things, then it means something is wrong. Everyone I know who uses Claude regularly, usually have the same esperience whenever I notice they degrade.

Show HN: MCP-wire – install and configure MCPs across multiple AI coding tools

andreagrandi — Thu, 19 Feb 2026 13:46:53 +0000

Article URL: https://github.com/andreagrandi/mcp-wire

Comments URL: https://news.ycombinator.com/item?id=47073655

Points: 4

# Comments: 0

New comment by andreagrandi in "Anthropic officially bans using subscription auth for third party use"

andreagrandi — Thu, 19 Feb 2026 13:23:15 +0000

I suspect you may not be writing code regularly... If I have to ask Claude the same things three times and it keeps saying "You are right, now I've implemented it!" and the code is still missing 1 out of 3 things or worse, then I can definitely say the model has become worse (since this wasn't happening before).

New comment by andreagrandi in "Anthropic officially bans using subscription auth for third party use"

andreagrandi — Thu, 19 Feb 2026 13:21:42 +0000

No, it's not the first time their models degrade for some time.