Hacker News: vntok

The Message from Deep Space

vntok — Sat, 04 Jul 2026 12:49:46 +0000

Article URL: https://store.steampowered.com/app/4080030/The_Message_from_Deep_Space/

Comments URL: https://news.ycombinator.com/item?id=48785051

Points: 1

# Comments: 0

New comment by vntok in "Half-Baked Product"

vntok — Fri, 03 Jul 2026 16:00:56 +0000

From the same guidelines:

> Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.

New comment by vntok in "Half-Baked Product"

vntok — Fri, 03 Jul 2026 15:57:06 +0000

Dishwasher? I hardly know her!

New comment by vntok in "Half-Baked Product"

vntok — Fri, 03 Jul 2026 15:50:17 +0000

This issue does not come from the coding assistant. In fact, humans will occasionally do the exact same thing as long as their tools have enough permissions to deploy to both local and prod from the same environment.

Fix it by separating the tools (different non-interconnected VMs, etc for dev/qa/preprod/prod environments) and the permissions (different accounts, sessions, tokens, etc for the run/debug/test/deploy loops).

New comment by vntok in "Have you restarted your computer this week?"

vntok — Wed, 01 Jul 2026 05:29:34 +0000

I'm running QubesOS, my various qubes reboot about a dozen times a day.

New comment by vntok in "Amazon CEO's talks with U.S. officials triggered crackdown on Anthropic models"

vntok — Sat, 13 Jun 2026 19:17:01 +0000

Indeed, the more accurate way to say it is that people in the US don't care enough about mass school shootings to do something about it besides thought and prayers.

New comment by vntok in "Show HN: FablePool – pool money behind a prompt, and Fable builds it in public"

vntok — Fri, 12 Jun 2026 16:08:10 +0000

That's even more expensive.

New comment by vntok in "Anthropic requires 30 day data retention for Fable and Mythos"

vntok — Thu, 11 Jun 2026 00:36:59 +0000

You must have very unrepresentative customers. What will they use?

New comment by vntok in "Anthropic requires 30 day data retention for Fable and Mythos"

vntok — Thu, 11 Jun 2026 00:35:26 +0000

Thank you for your service.

New comment by vntok in "A Farmer Donated Land to Turn into a Park. The City Is Building a Data Center"

vntok — Wed, 10 Jun 2026 22:30:29 +0000

The cooling towers are right there.

New comment by vntok in "A €0.01 bank transfer could compromise a banking AI agent"

vntok — Wed, 10 Jun 2026 22:26:59 +0000

Wait till you learn the bank routinely uses CSV as a non-ironic exchange format! That definitely is stochastic.

New comment by vntok in "A €0.01 bank transfer could compromise a banking AI agent"

vntok — Wed, 10 Jun 2026 19:55:06 +0000

Look up "prepared statements", it's pretty well documented.

New comment by vntok in "Google changes its search box"

vntok — Tue, 19 May 2026 20:43:39 +0000

Spreading malware to your website's visitors is wild and illegal in most jurisdictions. I certainly wouldn't confess about it online.

New comment by vntok in "Google changes its search box"

vntok — Tue, 19 May 2026 20:39:07 +0000

Well in addition to what you wrote, the marketing manager ALSO wasn't tracking any ad-related marketing performance indicator (CTR, CR, etc.) in any measurable way for very long periods of time... or they would have caught it almost immediately ("wow ad spend, CTR and CR have all suddenly gone down to 0/0% and have been staying there for days on all our campaigns! What's up with that?").

New comment by vntok in "OpenClaw Creator Spent $1.3M on OpenAI Tokens in 30 Days"

vntok — Sat, 16 May 2026 18:33:10 +0000

His restraint alone is commandable.

New comment by vntok in "OpenClaw Creator Spent $1.3M on OpenAI Tokens in 30 Days"

vntok — Sat, 16 May 2026 18:32:25 +0000

His team is basically him and two other humans, powering an ambitious well-known project so successful an industry titan ended up acquihiring him/them. That's pretty lean, no?

New comment by vntok in "How Claude Code works in large codebases"

vntok — Fri, 15 May 2026 14:11:21 +0000

Well, for starters the program you wrote is wrong (very unreliable) 100% of the time (very predictable)... so you just got your answer I guess.

In any case, most -if not nearly all- of the top-100 LLM will answer your prompt with some code that does what you intended the first program to do. Only they'll actually code it properly of course.

New comment by vntok in "How Claude Code works in large codebases"

vntok — Fri, 15 May 2026 10:27:32 +0000

> Are LLMs that super reliable in their output already with all the guardrails around?

Well, what is your definition of "super reliable in the output", and is it a quantifiable/measurable target or just a feeling?

Is it "more than humans", "more than senior developers", "almost perfect", "perfect"?

> It might behave differently than specified and a human is required to validate every output carefully or else.

Sure, just like meatbag developers. All the security flaws AI finds today were introduced years/decades ago by humans and haven't been found (that we know) by humans in ages.

New comment by vntok in "Googlebook"

vntok — Tue, 12 May 2026 22:51:56 +0000

Or maybe you can buy some stuff while visiting on holidays?

New comment by vntok in "Googlebook"

vntok — Tue, 12 May 2026 22:50:36 +0000

Ad blockers do absolutely nothing against fake reviews, fraudulent claims, sponsored articles and influencers manipulating you into buying stuff.