Hacker News: leobuskin

New comment by leobuskin in "Unicorn – The Ultimate CPU Emulator"

leobuskin — Tue, 16 Jun 2026 18:59:01 +0000

I’m using it a lot in AI-driven reverse-engineering (old DOS games), agents love it (usually Python harness)

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

leobuskin — Sat, 13 Jun 2026 12:48:09 +0000

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.

New comment by leobuskin in "Microsoft open-sources “the earliest DOS source code discovered to date”"

leobuskin — Sun, 24 May 2026 08:26:12 +0000

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

New comment by leobuskin in "Bun support is now limited and deprecated"

leobuskin — Fri, 22 May 2026 19:41:43 +0000

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?

New comment by leobuskin in "Bun support is now limited and deprecated"

leobuskin — Fri, 22 May 2026 19:28:50 +0000

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.

New comment by leobuskin in "Bun support is now limited and deprecated"

leobuskin — Fri, 22 May 2026 19:17:50 +0000

absolutely, and `its development seems to have taken a turn towards being fully vibe-coded` ungrounded claim confirms the hysteria, I'm afraid

New comment by leobuskin in "Flipper One – we need your help"

leobuskin — Thu, 21 May 2026 13:09:24 +0000

@zhovner, would you consider reverse engineering of the blobs as a temporary measure? in 2026 it's very doable and scales

New comment by leobuskin in "Agora-1: The Multi-Agent World Model"

leobuskin — Tue, 19 May 2026 09:20:19 +0000

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

New comment by leobuskin in "Agents Aren't Coworkers, Embed Them in Your Software"

leobuskin — Sun, 26 Apr 2026 01:22:03 +0000

> 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.

New comment by leobuskin in "An update on recent Claude Code quality reports"

leobuskin — Fri, 24 Apr 2026 04:40:42 +0000

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.

New comment by leobuskin in "Show HN: Every CEO and CFO change at US public companies, live from SEC"

leobuskin — Wed, 15 Apr 2026 14:47:12 +0000

What's the backend? I'd recommend to migrate such project to the edge (Cloudflare, etc)

New comment by leobuskin in "System Card: Claude Mythos Preview [pdf]"

leobuskin — Tue, 07 Apr 2026 19:02:27 +0000

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

New comment by leobuskin in "Meta acquires Moltbook"

leobuskin — Wed, 11 Mar 2026 01:44:38 +0000

In this new AI-driven world, ideas mean everything; one more year - it will be battles of ideas (not implementations as before).

New comment by leobuskin in "Doom in Django: testing the limits of LiveView at 600.000 divs/segundo"

leobuskin — Wed, 31 Dec 2025 10:58:18 +0000

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

New comment by leobuskin in "Doom in Django: testing the limits of LiveView at 600.000 divs/segundo"

leobuskin — Wed, 31 Dec 2025 10:55:14 +0000

It's only django-related third-party packages comparison (and SSR itself), would be a bit strange to compare with a different language/stack and/or framework

New comment by leobuskin in "Manus AI 100M USD ARR"

leobuskin — Sun, 28 Dec 2025 23:56:08 +0000

Never met a single person who used Replit/Lovable/Bolt/v0, all folks have either custom harnesses around top-tier labs' models, or use their dev-tools (cc, codex, etc). It feels like Manus & Co are very niche thing

New comment by leobuskin in "Django: what’s new in 6.0"

leobuskin — Wed, 10 Dec 2025 04:08:35 +0000

There’s no alternative (while prototyping), and anything else is better (when you properly defined your case).

New comment by leobuskin in "Django: what’s new in 6.0"

leobuskin — Wed, 10 Dec 2025 02:11:20 +0000

It's okay till it's not. Everyone I know who had Celery in production was looking for a substitution (custom or third-party) on a regular basis. Too many moving pieces and nuances (config × logic × backend), too many unresolved problems deep in its core (we've seen some ghosts you can't debug), too much of a codebase to understand or hack. At some point we were able to stabilize it (a bunch of magic tricks and patches) and froze every related piece; it worked well under pressure (thanks, RabbitMQ).

New comment by leobuskin in "Show HN: Runprompt – run .prompt files from the command line"

leobuskin — Thu, 27 Nov 2025 22:14:54 +0000

/usr/local/bin/promptrun

  #!/bin/bash
  file="$1"
  model=$(sed -n '2p' "$file" | sed 's/^# \*//')
  prompt=$(tail -n +3 "$file")
  curl -s https://api.anthropic.com/v1/messages \
    -H "x-api-key: $ANTHROPIC_API_KEY" \
    -H "content-type: application/json" \
    -H "anthropic-version: 2023-06-01" \
    -d "{
      \"model\": \"$model\",
      \"max_tokens\": 1024,
      \"messages\": [{\"role\": \"user\", \"content\": $(echo "$prompt" | jq -Rs .)}]
    }" | jq -r '.content[0].text'

hello.prompt

  #!/usr/local/bin/promptrun
  # claude-sonnet-4-20250514

  Write a haiku about terminal commands.

New comment by leobuskin in "Launch HN: JSX Tool (YC F25) – A Browser Dev-Panel IDE for React"

leobuskin — Wed, 12 Nov 2025 22:23:18 +0000

But here's the thing: most of your real audience doesn't have API keys (except a few enterprise-ish folks or startups who got credits). They already pay subscription(s) (and will continue to pay the maximum, which will keep growing). The entire token resale model creates a weird economy and interdependency that shouldn't exist in the first place. In the end, all the deals with top-tier labs will be changing, most middlemen will start manipulating the token exchange rate at some point, and there's no transparency or single source of trust. What's the Endspiel here?