Hacker News: Bullhorn9268

New comment by Bullhorn9268 in "US Schools Are Ditching Chromebooks for MacBooks by the Thousands"

Bullhorn9268 — Mon, 03 Aug 2026 16:34:15 +0000

Just seem it was a question of time.

Estimating the market value of top AI researchers

Bullhorn9268 — Thu, 16 Apr 2026 13:38:12 +0000

Article URL: https://futuresearch.ai/most-valuable-researchers/

Comments URL: https://news.ycombinator.com/item?id=47792780

Points: 11

# Comments: 0

New comment by Bullhorn9268 in "My minute-by-minute response to the LiteLLM malware attack"

Bullhorn9268 — Thu, 26 Mar 2026 17:03:29 +0000

The fact pypi reacted so quickly and quarantined the package in like 30 minutes after the report is pretty great!

New comment by Bullhorn9268 in "My minute-by-minute response to the LiteLLM malware attack"

Bullhorn9268 — Thu, 26 Mar 2026 15:57:33 +0000

Not a security researcher, but this is IMHO obviously positive that the other side of the arms race is also getting stronger, and I would argue it's stronger than on the bad guys' side, due to the best being somewhat responsible and adding guardrails.

I like the presentation <3.

New comment by Bullhorn9268 in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"

Bullhorn9268 — Wed, 25 Mar 2026 14:28:59 +0000

I am from futuresearch and went through this with Callum (the OG). We did a small analysis here: https://futuresearch.ai/blog/litellm-hack-were-you-one-of-th... of the packages and also build this mini tool to analyze the likelihood of you getting pwned through this: https://futuresearch.ai/tools/litellm-checker/

New comment by Bullhorn9268 in "LiteLLM PyPI has been compromised an hour ago, do not update"

Bullhorn9268 — Tue, 24 Mar 2026 12:20:10 +0000

yeah, updated in the post

LiteLLM PyPI has been compromised an hour ago, do not update

Bullhorn9268 — Tue, 24 Mar 2026 12:07:02 +0000

Article URL: https://futuresearch.ai/blog/litellm-pypi-supply-chain-attack/

Comments URL: https://news.ycombinator.com/item?id=47501431

Points: 27

# Comments: 5

New comment by Bullhorn9268 in "Claude Code's MCP config can silently orphan Docker containers"

Bullhorn9268 — Mon, 16 Mar 2026 14:13:40 +0000

So, is there a way of somehow cleaning up those docker containers, e.g. when uv version is not available?

New comment by Bullhorn9268 in "Inline MCP results are the new prompt bloat"

Bullhorn9268 — Wed, 11 Mar 2026 15:02:22 +0000

I believe cloudflare tries to work around that with Code Mode, right? https://blog.cloudflare.com/code-mode/ (but the OP is still useful for when classic MCP is needed)

New comment by Bullhorn9268 in "Caution: Read the Docs for Claude 4.6's Effort Parameter"

Bullhorn9268 — Tue, 10 Mar 2026 14:50:09 +0000

I see the value in making it simple for the user, but here I feel it's a bit too much. Would probably prefer two.

New comment by Bullhorn9268 in "I put my whole life into a single database"

Bullhorn9268 — Tue, 10 Mar 2026 13:22:58 +0000

I too learned this the hard way. I still haven't figured out why this is the case - like, is the inherent incidental irreducible complexity of human life too high, so it dominates majority of our actions?

Caution: Read the Docs for Claude 4.6's Effort Parameter

Bullhorn9268 — Tue, 10 Mar 2026 13:16:36 +0000

Article URL: https://everyrow.io/blog/claude-effort-parameter

Comments URL: https://news.ycombinator.com/item?id=47322866

Points: 8

# Comments: 2

New comment by Bullhorn9268 in "Good software knows when to stop"

Bullhorn9268 — Thu, 05 Mar 2026 17:40:05 +0000

I dislike spotify but weirdly enough I can never point out exactly what's so frustrating about it...

New comment by Bullhorn9268 in "What to Put in a Claude Code Skill for Reviewing Your Team's Code"

Bullhorn9268 — Thu, 05 Mar 2026 17:37:22 +0000

Weirdly, CC still adds stupid comments to guide its next steps despite having that instruction in CLAUDE.md AFAIK.

New comment by Bullhorn9268 in "What to Put in a Claude Code Skill for Reviewing Your Team's Code"

Bullhorn9268 — Thu, 05 Mar 2026 17:35:28 +0000

Maybe like that the humans would not properly review the more complicated ones too? I don't think it's a big danger to be clear.

New comment by Bullhorn9268 in "What to Put in a Claude Code Skill for Reviewing Your Team's Code"

Bullhorn9268 — Thu, 05 Mar 2026 17:33:09 +0000

Some of the rules are impossible to code generally enough, right? Like, "no defensive coding" - I can't imagine what kind of AST shenaningas you would have to do without basically banning `if`.

New comment by Bullhorn9268 in "What to Put in a Claude Code Skill for Reviewing Your Team's Code"

Bullhorn9268 — Thu, 05 Mar 2026 17:32:13 +0000

I mean, have you tried to ask it not to do those checks? It's similar to the OP about no defensive coding. In general, CC works better when you can tell it WHAT TO DO as opposed what NOT to do, but sometimes there is no way around it. What kind of checks it's adding? Like asserting that columns exist and stuff?

New comment by Bullhorn9268 in "A free tool to track and visualize your Wi-Fi connection coverage"

Bullhorn9268 — Sat, 03 Aug 2024 13:10:52 +0000

Hi. I created this tool wifi-heatmapper (https://github.com/hnykda/wifi-heatmapper/) to help me measure and track my WiFi connection at home. You upload a floorplan, click on it, and it generates heatmaps. All locally.

Hope some people find it useful!

A free tool to track and visualize your Wi-Fi connection coverage

Bullhorn9268 — Sat, 03 Aug 2024 13:10:52 +0000

Article URL: https://github.com/hnykda/wifi-heatmapper

Comments URL: https://news.ycombinator.com/item?id=41146442

Points: 4

# Comments: 2

New comment by Bullhorn9268 in "Show HN: FutureSearch – answer hard questions like "Who will buy TikTok US?""

Bullhorn9268 — Wed, 24 Apr 2024 06:58:00 +0000

Cool! Don't hesitate to reach out at hello@futuresearch.ai!