Hacker News: HumanOstrich

New comment by HumanOstrich in "GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance"

HumanOstrich — Sun, 05 Jul 2026 00:34:27 +0000

Anthropic is the one that prohibits harnesses other than Claude Code on subscription plans and bans users for disobeying.

OpenAI officially allows that with subscriptions.

New comment by HumanOstrich in "GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance"

HumanOstrich — Sat, 04 Jul 2026 23:52:22 +0000

If you bother to look at the issue instead of whining and complaining, you will see the evidence.

New comment by HumanOstrich in "Half-Baked Product"

HumanOstrich — Sat, 04 Jul 2026 17:57:33 +0000

Now this is the kind of honest snark I would hire.

New comment by HumanOstrich in "Potential session/cache leakage between workspace instances or consumer accounts"

HumanOstrich — Sat, 04 Jul 2026 15:41:20 +0000

What does this have to do with anything? Who are you talking to? This is Hacker News, not Anthropic support.

New comment by HumanOstrich in "Why frontier LLMs can't read the hard documents without experts involved"

HumanOstrich — Mon, 29 Jun 2026 15:22:47 +0000

Are you high?

New comment by HumanOstrich in "Why frontier LLMs can't read the hard documents without experts involved"

HumanOstrich — Mon, 29 Jun 2026 14:22:14 +0000

This is rather incoherent.

New comment by HumanOstrich in "We found a bug in the hyper HTTP library"

HumanOstrich — Mon, 29 Jun 2026 14:18:35 +0000

Order of magnitude more complexity.

New comment by HumanOstrich in "OAuth for all"

HumanOstrich — Fri, 26 Jun 2026 02:10:47 +0000

> OAuth is pretty simple, just read the spec.

You picked probably the only semi-straightforward thing about part of one of the OAuth specs, then hand-waved away the other 95% of the necessary related specs, knowledge, and experience for getting an implementation working robustly and securely for a non-trivial use case.

New comment by HumanOstrich in "32GB of DDR5 now costs $375 – AI shortage continues to squeeze PC building"

HumanOstrich — Wed, 03 Jun 2026 22:05:45 +0000

Great if you have fiber and live down the road from the datacenter.

New comment by HumanOstrich in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

HumanOstrich — Wed, 03 Jun 2026 21:04:28 +0000

We aren't talking about insect identification models from 2019.

New comment by HumanOstrich in "Cloudflare Turnstile requiring fingerprintable WebGL"

HumanOstrich — Mon, 01 Jun 2026 13:05:38 +0000

> I don't think I average even 2 captchas a day being terminally online, so 10 across every soul in the world sounds way too much for me. (we're ignoring bots it's meant to deter?)

You're mixing up checks, fingerprinting, and PoW with a captcha being triggered because those didn't pass. The less abnormal your setup is, the fewer captchas you'll get.

I agree with the rest of what you said.

Also I think you mean "scraper" and not "scrapper".

New comment by HumanOstrich in "Creatine raises brain energy levels and slows cognitive decline: study"

HumanOstrich — Sun, 31 May 2026 19:13:06 +0000

N=1 P=0.5

New comment by HumanOstrich in "Private equity bought America's essential services"

HumanOstrich — Thu, 28 May 2026 15:44:53 +0000

Replacing parts of PE firms with AI is so far from being a useful suggestion here.

New comment by HumanOstrich in "AMD pulls a bait-and-switch on Linux users with Vivado licensing changes"

HumanOstrich — Thu, 28 May 2026 14:47:27 +0000

I don't think gaming on Linux is comparable here.

New comment by HumanOstrich in "I’ve banned query strings"

HumanOstrich — Sun, 10 May 2026 01:46:10 +0000

Libraries that automatically throw errors for status codes in the 400 and 500 ranges are pretty obnoxious (looking at you, axios). It adds unnecessary overhead, complexity, and bad ergonomics by hijacking control flow from the app.

Responses with status codes in the 400 range are client errors, so the client shouldn't retry the same request. So a 404 is appropriate despite how annoying a library might be at handling it. Depending on which language/ecosystem you are using, there are likely more sane alternatives.

New comment by HumanOstrich in "Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc"

HumanOstrich — Sat, 09 May 2026 23:57:59 +0000

Yep, the Anthropic acquisition, this petulant Rust rewrite, and bun's increasingly buggy releases (slop) have caused me to migrate my projects (personal and work) to nodejs+pnpm.

The risks of using bun are no longer just those concerns around a newer tech and "drop-in" replacement for nodejs. Now you have to marry Anthropic, Rust, and a founder with conflicting priorities.

New comment by HumanOstrich in "Higher usage limits for Claude and a compute deal with SpaceX"

HumanOstrich — Wed, 06 May 2026 23:03:57 +0000

Hey Grok is pretty good for meme videos and pics. For anything serious, not so much.

New comment by HumanOstrich in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

HumanOstrich — Tue, 05 May 2026 17:35:17 +0000

That is.. inaccurate.

New comment by HumanOstrich in "Google Chrome silently installs a 4 GB AI model on your device without consent"

HumanOstrich — Tue, 05 May 2026 13:32:02 +0000

> This also makes it the only open American frontier-level model right now.

I'm not going to keep arguing with you. If you want to keep arguing, go to https://gemini.google.com/. Gemini knows what a frontier model is and it knows that Gemini Nano is fundamentally different from the other Gemini models. For one, it uses the Gemma architecture. And the next version of Gemini Nano is built directly on Gemma 4.

As for your original claim that I quoted, there are other "open American frontier-level models" by your definition. Like Gemma 4.

New comment by HumanOstrich in "Google Chrome silently installs a 4 GB AI model on your device without consent"

HumanOstrich — Tue, 05 May 2026 10:36:05 +0000

Thanks. Looks like the current Gemini Nano is actually a separate model with the Gemma 3n architecture that has been distilled from Gemini 2.5 Flash[1].

Also, the next version of Gemini Nano will be based directly on Gemma 4 (so not distilled, not Gemini at all except for the name)[2].

So no, it's not a frontier model. Those don't run on your phone or in your browser.

[1]: https://developer.android.com/blog/posts/ml-kit-s-prompt-api...

[2]: https://android-developers.googleblog.com/2026/04/AI-Core-De...