Hacker News: balefulboy

New comment by balefulboy in "GPT-6 Astra"

balefulboy — Thu, 03 Sep 2026 21:08:20 +0000

Well it's not exactly saturated when OAI refused to use the harness explicitly provided by ARC-AGI. I'm not really familiar enough with the benchmark to declare whether it's a perfect measure for AGI, but I kind of doubt it is.

New comment by balefulboy in "GPT-6 Astra"

balefulboy — Thu, 03 Sep 2026 21:03:38 +0000

Because they saw how much hype Glasswing was getting in April

New comment by balefulboy in "GPT-6 Astra"

balefulboy — Thu, 03 Sep 2026 21:02:10 +0000

I'm always tired of seeing at the top of every new model release post on here. I say Simon should just keep it to Twitter.

New comment by balefulboy in "GPT-6 Astra"

balefulboy — Thu, 03 Sep 2026 20:36:01 +0000

Don't forget the 3D demos. My favorite is in the house tour where the sink and stovetop(?) are obviously very misaligned from the counters

New comment by balefulboy in "GPT-6 Astra"

balefulboy — Thu, 03 Sep 2026 20:15:10 +0000

72 to 74 on DeepSWE is AGI

New comment by balefulboy in "GPT-5.6"

balefulboy — Thu, 09 Jul 2026 20:47:25 +0000

it seems the older models were capped at 10kusd for the runs though?

New comment by balefulboy in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

balefulboy — Sat, 13 Jun 2026 02:52:19 +0000

Damn, that beam of light was a flashbang. I wouldn't call this tasteful UI design, but maybe I just need to go to sleep.

New comment by balefulboy in ""Don't You Just Upload It to ChatGPT?""

balefulboy — Fri, 12 Jun 2026 22:10:02 +0000

Greentext is eh. Very formulaic, in fact very similar to the bottomless pit one, which I'd argue is better because of it's absurdity. I have to ask, did you mention the older GPT version to fable in the prompt?

New comment by balefulboy in "Mmorpg World of ClaudeCraft, vibe coded with Fable 5"

balefulboy — Fri, 12 Jun 2026 22:05:30 +0000

i got a 502

New comment by balefulboy in "Policy on the AI Exponential"

balefulboy — Wed, 10 Jun 2026 21:25:06 +0000

METR's time horizon is not a reliable metric of LLM capability growth: https://www.transformernews.ai/p/against-the-metr-graph-codi...

New comment by balefulboy in "Claude Fable 5"

balefulboy — Tue, 09 Jun 2026 21:58:37 +0000

yeah man this sucks. i genuinely do not know how people find this stuff appealing

New comment by balefulboy in "Ask HN: Why won't you be replaced by AI?"

balefulboy — Mon, 08 Jun 2026 21:35:41 +0000

I still don't know why people are saying this. I don't really code but from what I've heard on here the models haven't improved since Opus 4.5