Hacker News: throwaway314155

New comment by throwaway314155 in "Google Playground: Create and play custom games"

throwaway314155 — Wed, 07 Oct 2026 15:33:59 +0000

Getting a 403 in the US.

New comment by throwaway314155 in "Claude Code’s suggested message feature: I think the real customer is the model"

throwaway314155 — Wed, 07 Oct 2026 15:05:18 +0000

> I also like how feedback is collected. It prompts to press 1, 2, or 3 to rate how well Claude is doing...

I commonly respond to Claude with a numbered list of critiques. The number of times I have accidentally rated something when I would have rather push "0" for "go away" is infuriating.

New comment by throwaway314155 in "AnyPS5: Port PS5 binaries to PC without emulation (87% system libraries mapped)"

throwaway314155 — Wed, 07 Oct 2026 02:49:41 +0000

> at least on a wired connection

There goes 95% of your market. If not more.

New comment by throwaway314155 in "Muse Gadgets"

throwaway314155 — Sat, 03 Oct 2026 01:16:01 +0000

Threads is shit.

New comment by throwaway314155 in "Sites in ChatGPT"

throwaway314155 — Fri, 02 Oct 2026 19:29:10 +0000

Put them in a .env file and tell it to never look there but what the env vars are named. Problem solved.

New comment by throwaway314155 in "Sites in ChatGPT"

throwaway314155 — Fri, 02 Oct 2026 19:26:16 +0000

Oh come on. Sure, it might not be a production-capable system. But comparing an Astra 6/Sol 6.1 powered sites to wordpress and wix is apples and oranges.

New comment by throwaway314155 in "Introducing System One Models and Jev"

throwaway314155 — Wed, 16 Sep 2026 08:32:22 +0000

That's clever and all - solid setup, good work. But I still think you either overestimate the average house guest or have particularly savvy/young house guests.

New comment by throwaway314155 in "No Man's Sky Cosmos"

throwaway314155 — Wed, 09 Sep 2026 22:06:32 +0000

No Man's Sky and Cyberpunk 2077 are actually proof you can have an awful launch and still pivot into a large player base and continued sales via updates.

Reception for both games is largely positive despite their poor initial response.

New comment by throwaway314155 in "ChatGPT Images 2.5"

throwaway314155 — Tue, 08 Sep 2026 21:46:37 +0000

> that distinct off-white shading

Let's see Paul Allen's card.

New comment by throwaway314155 in "OpenAI begins rolling out GPT-6 Astra"

throwaway314155 — Thu, 03 Sep 2026 19:45:21 +0000

Is it expected to be available to subscribers?

New comment by throwaway314155 in "Apple caught off guard by AI demand for Mac Mini and Mac Studio"

throwaway314155 — Mon, 31 Aug 2026 18:10:25 +0000

> You have good enough hardware to run good models comparable with Gemini and ChatGPT.

That is at best misleading and at worst outright misinformation.

New comment by throwaway314155 in "Breaking Claude Code Opus 5 Auto Mode"

throwaway314155 — Mon, 31 Aug 2026 16:50:39 +0000

Your emphasis here seems to downplay the end-result of the attack - which is arbitrary code execution from a seemingly innocent URL merely being read by the LLM. The ACE is pulled off without the user knowing, and seemingly without agent or its auto-mode classifier knowing. There are at the very least _elements_ of prompt injection/jailbreaking in here. The LLM reads content and performs actions described failing to stop itself.

New comment by throwaway314155 in "Python's pre-declared constants are kinda weird"

throwaway314155 — Wed, 26 Aug 2026 01:09:40 +0000

Queue the hoards of Python haters apparently.

New comment by throwaway314155 in "Watch Tesla FSD v14 Lite drive over a giant log without stopping"

throwaway314155 — Tue, 25 Aug 2026 23:54:11 +0000

This website is the worst.

New comment by throwaway314155 in "Where did all the public bathrooms go?"

throwaway314155 — Tue, 25 Aug 2026 12:16:18 +0000

> They're all in Tokyo ;)

Yeah and effectively any store outside urban America.

New comment by throwaway314155 in "Nvidia AVO scores 100% on the ARC-AGI-3 interactive reasoning benchmark"

throwaway314155 — Fri, 21 Aug 2026 14:59:33 +0000

I don't think GPT-4 was ever used for beating pokemon with or without a harness. Successful attempts include Gemini 2.5 and Opus 4.7 both using relatively advanced custom harnesses that give access to game memory, notes systems, and one-off hacks to get around parts of the game the model gets stuck on. More recently, Fable 5 beat FireRed with a _very_ minimal harness (screenshots and button inputs). That's the only example I know of but that is a very sophisticated and very expensive model compared to GPT-4.

Most of this doesn't discredit your overall point, though.

New comment by throwaway314155 in "Vomit: Clean up Claude 5's token output with a separate LLM"

throwaway314155 — Thu, 20 Aug 2026 17:43:45 +0000

I'd expect this to cycle between companies ~monthly until they all IPO. As it turns out people do sometimes prefer speed and better UX. If the model (Sol, for now) has fewer parameters and also happens to be capable of solving deeply complex Fable-adjacent problems sometimes, even better.

New comment by throwaway314155 in "Message your other Claude Code sessions"

throwaway314155 — Fri, 14 Aug 2026 09:23:35 +0000

I take this back. Apparently the codex conversations are indeed stored in jsonl files in the users .codex directory.

New comment by throwaway314155 in "Grok 4.6 scores 61 on the Artificial Analysis Intelligence Index"

throwaway314155 — Thu, 13 Aug 2026 01:34:21 +0000

Isn't this a _good_ thing??

New comment by throwaway314155 in "Message your other Claude Code sessions"

throwaway314155 — Sun, 09 Aug 2026 10:50:40 +0000

You can have Codex access Claude’s conversations trivially. The other way around not so much as OpenAI locks everything server side.