Hacker News: leobuskin

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Sat, 15 Aug 2026 10:03:29 +0000

Heretic?

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Sat, 15 Aug 2026 06:56:33 +0000

That’s the first model that fits CC as it’s own, zero issues, but probably ZCode or whatever z.ai’s cli is.

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 15:53:41 +0000

On $80 plan 200M tokens ~20% of weekly usage

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 15:15:07 +0000

It’s comparable to Anthropic usage, to be honest. 2x GLM agents ate 18% of weekly usage on this mid-tier plan within ~8 hrs (non-stop work, a lot of tool calls, appx 4 compactions each), I think. I didn’t make a proper statistics snapshot, sorry.

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 13:55:39 +0000

https://docs.z.ai/devpack/latest-model#switching-models-in-c...

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 13:29:36 +0000

In what scenarios?

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 13:05:48 +0000

I’ve tried a bunch of them, and I seriously do not understand these recommendations. It was a rough road and a steep hill, but right now CC is absolutely the best harness on the market, as for me, whatever top tier model is under the hood (mostly, some of them, like DeepSeek, don’t fit CC at all).

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 13:01:22 +0000

Fable wasn’t trained on github commits, let’s be fair.

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 12:22:08 +0000

Impossible with source code, possible to bypass with app/site

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 12:01:29 +0000

Exactly my CoT! I hope z.ai won’t change this behavior after training it on our input the same way as Anthropic did (shame on you, folks, seriously)

New comment by leobuskin in "GLM-5.3: Frontier coding with emergent cyber capabilities"

leobuskin — Fri, 14 Aug 2026 11:48:31 +0000

I bought $18 GLM official subscription yesterday (5.2, but new model version was already leaking on some docs), set it up with Claude Code harness... and I’ve bumped to $80 plan almost immediately. It’s the first model that agreed on a proper security research (red team scenario), executed it seamlessly, including 0-days in WP plugins, RCE, 6.8 kernel exploit adaptation, etc - while playing against another GLM agent as a defender (following HF story)!

I understand that such models can be used by malicious actors, but it’s fair to have it publicly available (and play on your side in case of emergency). This is what changes the world in a better way, I think, not the guardrails.

New comment by leobuskin in "How is the Bun rewrite in Rust going?"

leobuskin — Mon, 27 Jul 2026 13:07:53 +0000

Nope, they want shared artifact(s) between web and desktop (not sure what do they have in mobile apps) clients (Chat/Cowork/Code/CC-cli), so TS is the way to go. It’s a reasonable choice made by engineers.

New comment by leobuskin in "Claude Opus 5"

leobuskin — Fri, 24 Jul 2026 18:41:10 +0000

Is it some Claude Team/Enterprise only problematic? I'm using two 20x Max accounts almost non-stop (Fable/Opus) for 1.5 years at this point, zero issues with both client and infra sides (from US and in travels). When I'm reading such messages it feels like either I'm lucky or it's a part of some campaign.

New comment by leobuskin in "First atmosphere found on Earth-like planet in habitable zone of distant star"

leobuskin — Sat, 18 Jul 2026 08:06:34 +0000

If I understand correctly, time spent within this interstellar ship reference frame would be significantly less than 75k years. And at 1c speed, 48 years on Earth would be ~2 years of "flight" for the passengers, correct me if I'm wrong.

New comment by leobuskin in "Claude Code: Anatomy of a Misfeature"

leobuskin — Fri, 17 Jul 2026 17:24:29 +0000

Is there a way to turn options-based AskUserQuestion off? I couldn't find it at all, and the "options" selector is the most annoying thing in CC for me, plain-text is the only way, everything else is distracting. I know, I can use `n` (sometimes) or cancel it, but both bring more pain that just regular communication (cancellation does one more chat step + requires an extra action, same with `n`)

New comment by leobuskin in "We're extending access to Fable 5 on all paid plans through July 12"

leobuskin — Wed, 08 Jul 2026 04:41:31 +0000

That's not a bailout for AI labs, I meant the "bailout" for Salesforce and others. There's absolutely no place for them in the world where we have Fable+ models. For many of them. Most of them (we just didn't get this feeling yet). Someone just trying to maintain the old world order, that's all. I don't think US economy would fail if those absolutely useless giants would go down.

New comment by leobuskin in "We're extending access to Fable 5 on all paid plans through July 12"

leobuskin — Wed, 08 Jul 2026 04:17:10 +0000

@anthropic, can you finally add $800-$1000 per month plan and allow us to work instead of tracking your weekly changes and dramas? I think, we (individuals, small-medium biz, first of all) did our best to help you train the model like Fable. Enterprise-level lockdown (and API costs define this) is... unfair? I mean, we all knew that you all will just use us, but it's AI, right? For people, right? Right?

The only reason this is happening -> someone (US gov?) decided that it's time to bail out those who would inevitably die within a year or two otherwise, middlemen.

New comment by leobuskin in "Python 3.14 compiled to metal – no interpreter"

leobuskin — Tue, 07 Jul 2026 00:54:57 +0000

Mojo folks created a new language, officially called it "superset", and trying to sell to enterprise. And it's not a superset by definition, because it can't run it's "subset" (the original Python) without CPython (which was used as libcpython under the hood, iirc). It's a travesty.

New comment by leobuskin in "Python 3.14 compiled to metal – no interpreter"

leobuskin — Mon, 06 Jul 2026 21:20:20 +0000

It uses JIT

New comment by leobuskin in "Python 3.14 compiled to metal – no interpreter"

leobuskin — Mon, 06 Jul 2026 21:15:05 +0000

It passes only curated corpus (snippets), not the full CPython test suite. So, yes, reading is hard. Nothing against AI, btw.