Hacker News: eaf7e281

New comment by eaf7e281 in "Anthropic downgraded cache TTL on March 6th"

eaf7e281 — Sun, 12 Apr 2026 21:39:37 +0000

i mean, openai does same, even worse, they change the model, like gpt 5.4 to -mini

anthropic for now, at least just seems to change quantization of the model

New comment by eaf7e281 in "Happy Map"

eaf7e281 — Sun, 12 Apr 2026 18:50:19 +0000

A happy map that makes me sad.

New comment by eaf7e281 in "Anthropic downgraded cache TTL on March 6th"

eaf7e281 — Sun, 12 Apr 2026 13:25:28 +0000

I think they changed the quantification to save computer power for their new model. This might be why the benchmark scores look good, but the real world performance is much worse. I'm wondering if they're testing the model internally and didn't find anything wrong with the new parameter.

I canceled my subscription and switched to a codex, but it's not as good. I'm tired of Anthropic changing things all the time. I use Claude because it doesn't redirect you to a different model like OpenAI does. But now it seems like both companies are doing the same thing in different way.

New comment by eaf7e281 in "How we rebuilt Next.js with AI in one week"

eaf7e281 — Tue, 24 Feb 2026 22:38:59 +0000

again?

New comment by eaf7e281 in "Spain’s LaLiga has blocked access to freedom.gov"

eaf7e281 — Mon, 23 Feb 2026 03:51:13 +0000

freedom is not coming

New comment by eaf7e281 in "Claude Opus 4.6"

eaf7e281 — Thu, 05 Feb 2026 21:25:55 +0000

It's hard to say. Maybe it has to do with the way Claude responds or the lack of "thinking" compared to other models. I personally love Claude and it's my only subscription right now, but it just feels weird compared to the others as a personal assistant.

New comment by eaf7e281 in "Orchestrate teams of Claude Code sessions"

eaf7e281 — Thu, 05 Feb 2026 21:17:58 +0000

These two basically do what you want, let Claude be the manager and Codex/Gemini be the worker. Many say that Coder-Codex-Gemini is easier to understand than CCG-Workflow, which has too many commands to start with.

https://github.com/FredericMN/Coder-Codex-Gemini https://github.com/fengshao1227/ccg-workflow

This one also seems promising, but I haven't tried it yet.

https://github.com/bfly123/claude_code_bridge

All of them are made by Chinese dev. I know some people are hesitant when they see Chinese products, so I'll address that first. But I have tried all of them, and they have all been great.

New comment by eaf7e281 in "Claude Opus 4.6"

eaf7e281 — Thu, 05 Feb 2026 18:16:31 +0000

I kinda agree. Their model just doesn't feel "daily" enough. I would use it for any "agentic" tasks and for using tools, but definitely not for day to day questions.

New comment by eaf7e281 in "Claude Opus 4.6"

eaf7e281 — Thu, 05 Feb 2026 18:14:10 +0000

> From the press release at least it sounds more expensive than Opus 4.5 (more tokens per request and fees for going over 200k context).

That's a feature. You could also not use the extra context, and the price would be the same.

New comment by eaf7e281 in "Claude Opus 4.6"

eaf7e281 — Thu, 05 Feb 2026 18:11:14 +0000

There's no way they actually work on training this.

New comment by eaf7e281 in "Disk Prices"

eaf7e281 — Thu, 16 Oct 2025 16:47:48 +0000

What is the optimal disk size in terms of price per TB? The last time I checked, it was 16 TB disks, I believe.