HNHacker News
TopNewBestAskShowJobs

leobuskin

361 karma · joined April 10, 2025

leonardbuskin [at] gmail
submissionscomments
leobuskin··on GLM-5.3: Frontier coding with emergent cyber capabilities
Fable wasn’t trained on github commits, let’s be fair.
leobuskin··on GLM-5.3: Frontier coding with emergent cyber capabilities
Impossible with source code, possible to bypass with app/site
leobuskin··on GLM-5.3: Frontier coding with emergent cyber capabilities
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)
leobuskin··on GLM-5.3: Frontier coding with emergent cyber capabilities
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.

leobuskin··on How is the Bun rewrite in Rust going?
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.
leobuskin··on Claude Opus 5
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.
leobuskin··on First atmosphere found on Earth-like planet in habitable zone of distant star
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.
leobuskin··on Claude Code: Anatomy of a Misfeature
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`)
leobuskin··on We're extending access to Fable 5 on all paid plans through July 12
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.
leobuskin··on We're extending access to Fable 5 on all paid plans through July 12
@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.

leobuskin··on Python 3.14 compiled to metal – no interpreter
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.
leobuskin··on Python 3.14 compiled to metal – no interpreter
It uses JIT
leobuskin··on Python 3.14 compiled to metal – no interpreter
It passes only curated corpus (snippets), not the full CPython test suite. So, yes, reading is hard. Nothing against AI, btw.
leobuskin··on Python 3.14 compiled to metal – no interpreter
It's possible, but we're at the moment when most of us can ask Fable to implement a custom compiler to a custom target for our favorite language, and even use it as a part of custom solution. Why do I need someone else's implementation? Where's the magic in this project? What's the secret sauce?
leobuskin··on Python 3.14 compiled to metal – no interpreter
A few problems with this Fable's project:

1. It's not Python by any means, it's a subset with its own runtime, its own quirks and nuances;

2. It will be impossible to maintain parity with CPython without AI assistance;

3. It will die the same way as dozens of similar (even non-AI projects) died before, and reasons will be the same: (1) and (2).

leobuskin··on Show HN: Nub – A Bun-like all-in-one toolkit for Node.js
“If you are already vibe-coded in Rust”, probably is better, Nub has a strong smell all the way (which is ok, just funny to compare with Bun).

P.S. The entire Bun’s anti-AI hysteria makes me very sad, sometimes it feels like a directed campaign

leobuskin··on Unicorn – The Ultimate CPU Emulator
I’m using it a lot in AI-driven reverse-engineering (old DOS games), agents love it (usually Python harness)
leobuskin··on Statement on US government directive to suspend access to Fable 5 and Mythos 5
It's a pretty big difference in quality, definitely no. I'll miss Fable a lot, it was the first time when the model was able to catch up with my abandoned compiler project, and it did it extremely well, I have seen nothing like this so far.
leobuskin··on Microsoft open-sources “the earliest DOS source code discovered to date”
I've used Claude to fix/reconstruct & build leaked Win2k3 on Linux with original toolchain via Wine. This approach included full gdi sources reconstruction. I just don't know what to do with this, it's kinda difficult to "wash" on this scale
leobuskin··on Bun support is now limited and deprecated
I apologize, may I ask you, do you use Bun? If yes, you probably do monitor the development of this project (I do, it sounds reasonable to track your tools/deps), probably familiar with Jared's coding style, decision making process, architecture nuances, previous choices? Do you have any issues opened/closed in Bun's repo? Were you satisfied with contributors' reaction? Do you feel you can trust devteam behind Bun?
leobuskin··on Bun support is now limited and deprecated
I'm afraid "we" tackle (agressively) the wrong problem, also making it's tough for the maintainers, who did nothing wrong (I have a lot of sympathy towards Bun's developers, they got a lot of ugly feedback within the last month). I don't think AI-written code is the problem at all. Human signs off the changeset the same way as it happened before. I don't care if Rust rewrite did happen using pipeline/harness and LLMs, if the maintainer takes responsibility, and in projects like Bun it happens "by default", I think.
leobuskin··on Bun support is now limited and deprecated
absolutely, and `its development seems to have taken a turn towards being fully vibe-coded` ungrounded claim confirms the hysteria, I'm afraid
leobuskin··on Flipper One – we need your help
@zhovner, would you consider reverse engineering of the blobs as a temporary measure? in 2026 it's very doable and scales
leobuskin··on Agora-1: The Multi-Agent World Model
Gamepads usage doesn't match screen actions/movements through the entire presentation video(s), zero trust at this point.

Edit: I apologize, entirely missed the game itself, partially understand the mismatch now, but still, it's much heavier in the presentation than in real life for some reason

leobuskin··on Agents Aren't Coworkers, Embed Them in Your Software
> Agentic management software is all the hype today: What started with Moltbot and OpenClaw now has a lot of competition: ZeroClaw, Hermes, AutoGPT etc.

Moltbot is OpenClaw, AutoGPT was born significantly before. I just couldn’t read after the first paragraph, I’ve lost the trust entirely, whatever/whoever wrote it.

leobuskin··on An update on recent Claude Code quality reports
This usage reset you did on April 23 will not mitigate the struggle we’ve experienced. I didn’t even notice it yesterday. I checked this morning and it came down from 25% weekly to 7%. What is this? I didn’t have problems for two months like many others (maybe my CC habits helped), but two weeks were very painful. Make a proper apology, guys. This “reset” for many users could hit the first days of the week, tell me you thought about that.
leobuskin··on Show HN: Every CEO and CFO change at US public companies, live from SEC
What's the backend? I'd recommend to migrate such project to the edge (Cloudflare, etc)
leobuskin··on System Card: Claude Mythos Preview [pdf]
And as a bonus: GPT is slow. I’m doing a lot of RE (IDA Pro + MCP), even when 5.4 gives a little bit better guesses (rarely, but happens) - it takes x2-x4 longer. So, it’s just easier to reiterate with Opus
leobuskin··on Meta acquires Moltbook
In this new AI-driven world, ideas mean everything; one more year - it will be battles of ideas (not implementations as before).
leobuskin··on Doom in Django: testing the limits of LiveView at 600.000 divs/segundo
you can do it on wasmer's workers, their last wasm/python approach is pretty solid (compatibility, performance). it's sad to say, but after 4 years of "beta" Python support on CF workers - it's still ugly. I dunno who was responsible for such a neglect, but even with the last changes - total fiasco
← PreviousPage 2 of 3Next →