Hacker News: maxignol

Show HN: Route Claude Desktop to several accounts

maxignol — Wed, 14 Oct 2026 07:57:36 +0000

Article URL: https://github.com/jaynlabs/jaynshare

Comments URL: https://news.ycombinator.com/item?id=50083983

Points: 1

# Comments: 0

New comment by maxignol in "Ask HN: How do you describe what your relationship brings you?"

maxignol — Fri, 09 Oct 2026 12:03:16 +0000

To truly live as a couple, not as two individuals together I'd say then ?

New comment by maxignol in "Show HN: Codex and Claude subscriptions pooled together with whoever you trust"

maxignol — Fri, 09 Oct 2026 12:00:44 +0000

Currently, only claude code and codex in cli, soon Claude Desktop as well.

New comment by maxignol in "Ask HN: How do you describe what your relationship brings you?"

maxignol — Wed, 07 Oct 2026 15:45:35 +0000

> And one of the hardest optimization problems of being human is deciding who to love.

I truly agree. But then what do you look for in a relationship ? Cause to any optimization problems there are constraints and an objective function to push the metaphor ?

New comment by maxignol in "Show HN: Draw from your friends' Claude quota"

maxignol — Wed, 07 Oct 2026 14:35:15 +0000

Well, the software for now is designed for trusted groups of users, so appart from making sure users can't access sessions of others in the same pool, there's not much.

For context, it's sent in every request of claude code and codex (only in http, not websocket) so we don't have to handle anything, the server just rewrites the auth headers of the request, keeping it intact out of that.

New comment by maxignol in "Show HN: Draw from your friends' Claude quota"

maxignol — Wed, 07 Oct 2026 14:31:24 +0000

We've not found a way to make it completely legal yet but working on it lol

New comment by maxignol in "Ask HN: How do you describe what your relationship brings you?"

maxignol — Wed, 07 Oct 2026 14:19:55 +0000

Hope you'll find someone with whom this will be different

New comment by maxignol in "Ask HN: How do you describe what your relationship brings you?"

maxignol — Tue, 06 Oct 2026 20:44:48 +0000

Thank you for the reply

Ask HN: How do you describe what your relationship brings you?

maxignol — Tue, 06 Oct 2026 19:46:27 +0000

I've been struggling to put into words what I want from my relationships and began asking my friends what their answers were, and so now I ask you.

Comments URL: https://news.ycombinator.com/item?id=49983113

Points: 8

# Comments: 11

Show HN: Codex and Claude subscriptions pooled together with whoever you trust

maxignol — Mon, 05 Oct 2026 18:58:32 +0000

Article URL: https://github.com/jaynlabs/jaynshare

Comments URL: https://news.ycombinator.com/item?id=49968951

Points: 3

# Comments: 2

New comment by maxignol in "Show HN: Share Claude Code rate-limits between friends"

maxignol — Tue, 29 Sep 2026 16:24:04 +0000

Hi ! It's been a few months since with my best friend (and cofounder) we were really getting sick of one rate limiting while the other had plenty of "tokens" left on his Claude subscription. So we made this. And we find it cool so we share it to you.

Please give us feedback, that'd be really appreciated, negative or positive ;)

Show HN: Share Claude Code rate-limits between friends

maxignol — Tue, 29 Sep 2026 16:22:03 +0000

Article URL: https://github.com/jaynlabs/jaynshare

Comments URL: https://news.ycombinator.com/item?id=49895933

Points: 1

# Comments: 1

New comment by maxignol in "Caveman prompting saves tokens, until you run it in real sessions"

maxignol — Fri, 21 Aug 2026 16:11:50 +0000

Author here. Two things that are worth repeating up front: corpus A is 84% of the pooled bill, so the pooled −0.01% is pretty much "corpus A plus noise" so read it per-rows instead. And p_fire is a lower bound because of the detector's sensitivity taken as 1 (which it obviously isn't). Caveman's real fire rate is somewhat higher than 50.6%. Code and commands: github.com/jaynapp/jayn-caveman

Caveman prompting saves tokens, until you run it in real sessions

maxignol — Fri, 21 Aug 2026 16:11:18 +0000

Article URL: https://jayn.app/caveman

Comments URL: https://news.ycombinator.com/item?id=49390227

Points: 3

# Comments: 1

New comment by maxignol in "LinkedIn CringeBot 3000"

maxignol — Wed, 12 Aug 2026 08:34:35 +0000

> I don't know if engaging with that button means I'm less likely to be served such content, or whether it's cleaning up everyone's feeds.

I would guess it's both cause I've been having less AI slop on LinkedIn for the past few weeks (yet not none).

New comment by maxignol in "LinkedIn CringeBot 3000"

maxignol — Wed, 12 Aug 2026 08:32:16 +0000

Been laughing for the past 10 minutes, thanks for this one. (I tried the death of my cat by car in front of my house in a Go Girl manner, absolute cinema)

New comment by maxignol in "Meta Muse Glimmer – open weights 30B local coding model"

maxignol — Mon, 10 Aug 2026 11:12:55 +0000

Optimizing speed is really the way to go. Yet 24GB is not what everyone can afford. Maybe we could take some of those 56tk/s and transfer into some free RAM space using MoE loading ? I'd be glad with a less than 10GB and more than 6tk/s model.

New comment by maxignol in "Launch HN: Tokenless (YC S26) – Automatic model switching to save money"

maxignol — Wed, 29 Jul 2026 17:25:26 +0000

Is the model picked through the router only for the first user turn or is there multi-turn routing (or planned to be added) ?

New comment by maxignol in "Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac"

maxignol — Wed, 29 Jul 2026 16:29:00 +0000

I'm really excited about what's been happening couple last weeks for local inference. I feel like it all started after colibri [1] was released. Great work !

Anyone got recommendation about what local model to use for what purpose ? I feel like (as they were saying in moonshot blog post [2]) each llm can be an expert in its own categories and with several small local we might get good coverage for decent usage, granted each one is specialized enough.

[1] : https://github.com/JustVugg/colibri [2] : https://fireworks.ai/blog/kimik3-fable

New comment by maxignol in "Kimi-K3 on HuggingFace"

maxignol — Mon, 27 Jul 2026 10:16:25 +0000

I dont quite understand why GGUF is better optimized. Are the performances better for the same amount of VRAM ?