Hacker News: zihotki

New comment by zihotki in "What the Fuck Happened to Nerds"

zihotki — Mon, 15 Jun 2026 12:44:56 +0000

Isn't that exactly the marketing part? He is the marketing and the channel, he has optimized marketing process.

New comment by zihotki in "Microsoft's open source tools were hacked to steal passwords of AI developers"

zihotki — Tue, 09 Jun 2026 08:42:34 +0000

And the best recommendation security teams can give - keep your SBOM strict, use min release age policy (sounds more like band-aid). That's a scary world to live in.

New comment by zihotki in "Changing how we develop Ladybird"

zihotki — Fri, 05 Jun 2026 10:38:51 +0000

I wonder if adding an artificial barrier in form of a donation could help. That's probably the only remaining way to show the good faith.

New comment by zihotki in "AI Agent Guidelines for CS336 at Stanford"

zihotki — Mon, 01 Jun 2026 20:55:39 +0000

Pencil and paper - that's the classical way a lot of developers from western europe were taught to code. Back to the basics

New comment by zihotki in "Anthropic's "Profitability" Swindle"

zihotki — Fri, 22 May 2026 20:10:19 +0000

> To screw with OpenAI's IPO?

That's actually a very interesting idea. At least it could be a cherry on a cake given he lost the lawsuit with OpenAI.

New comment by zihotki in "Show HN: Spec-Driven Development Workflow for Claude Code"

zihotki — Fri, 22 May 2026 07:52:37 +0000

Are there any benchmarks/evals to see if this particular one is doing anything good comparing to, let's say, plan mode? How do you measure it actually works and you don't waste tokens and your personal time?

I fail to see any backing for claims 'boosting performance' and 'keeping costs low'

New comment by zihotki in "Google's Antigravity Bait and Switch"

zihotki — Thu, 21 May 2026 16:07:05 +0000

Wait, that's actually a great feature. Let me contact a friend in Google and make a suggestion..

New comment by zihotki in "Show HN: The AI Quant Desk for Onchain Finance"

zihotki — Wed, 20 May 2026 10:21:19 +0000

> Crypto is fast. Markets move violently. Complexity is accelerating. > Most users discover risk only after damage is done.

and then

> Resonance Labs (BVI) Limited > 2nd Floor, Ellen L. Skelton Building, > Fishers Lane, Road Town, > Tortola, British Virgin Islands, VG 1110

This sounds very fishy

New comment by zihotki in "Anthropic Is Preparing for IPO and We Should Be Worried"

zihotki — Tue, 19 May 2026 15:06:03 +0000

MS is more like assembling the surfaces, it's not the same as having a full vertical integration like Apple is trying to achieve with their contracts with Intel, in-house modem, etc.

New comment by zihotki in "Intro to TLA+ for the LLM Era: Prompt Your Way to Victory"

zihotki — Tue, 19 May 2026 14:58:34 +0000

I think that's what author implies by this sentence in the intro:

> It’s still your responsibility to understand your system and define what “correctness” means, and you need a high-level understanding of temporal logic.

New comment by zihotki in "What political censorship looks like inside an LLM's weights (Qwen 3.5)"

zihotki — Tue, 19 May 2026 07:20:13 +0000

It's an unreadable word soup in general

New comment by zihotki in "Setting up an AI-native organization"

zihotki — Sat, 16 May 2026 11:03:21 +0000

I'll wait for the follow up posts "setting up reasonable budgets for ai-native organization" and "validating (benchmarks/evals) that your ai-native setup has any benefit over a simplistic ai-assisted org"

New comment by zihotki in "Show HN: AI that audits your codebase in 60 seconds"

zihotki — Sat, 16 May 2026 08:45:08 +0000

> Powered by Gemini 1.5 Pro

full slope

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

zihotki — Fri, 15 May 2026 10:44:04 +0000

How do you make it so that the model doesn't forget to follow those rules and skills? How do you make it actually understand the architecture and constraints? You can't, current models don't work that way to make it happen.

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

zihotki — Fri, 15 May 2026 10:40:38 +0000

I wonder if Anthropic tested their claims on a pro, 5x, 20x subscriptions. When you have infinite amount of free tokens it sure makes sense, you just throw tokens at the problem. But not in a limited usage scenarios it doesn't fly far..

New comment by zihotki in "A Claude Code and Codex Skill for Deliberate Skill Development"

zihotki — Thu, 14 May 2026 08:01:23 +0000

No benchmarks and evals present, how do you know it produces better result than /create-skill ? Naive testing doesn't provide any confidence

New comment by zihotki in "European governments: 3.000 tracking sites, 1.000 phpMyAdmins, and 99% poorly"

zihotki — Wed, 13 May 2026 08:00:29 +0000

That's a wonderful initiative! I wanted first to complain about Dutch municipalities but looking at the foundation, I see fellow dutch- and belgian-men are already focusing on them!

New comment by zihotki in "Google Cloud Fraud Defence is just WEI repackaged"

zihotki — Fri, 08 May 2026 16:53:21 +0000

And the people will be just simply fired for underperforming. Or anything else, it's easy when you have at will employment.

New comment by zihotki in "Google Chrome silently installs a 4 GB AI model on your device without consent"

zihotki — Tue, 05 May 2026 11:06:33 +0000

Better not, it's too buggy and sluggish, it's more in a beta stage on desktop. I've been using it for the last year but not anymore.

New comment by zihotki in "Investors pile into clean energy as Iran war drives push for energy security"

zihotki — Sun, 03 May 2026 16:53:59 +0000

Keep in mind that heat pumps have a limit how much they can pump (it also depends on temp., there is less heat in 35F air). If your house is not well insulated, at a lower temperature it would be loosing more energy and eventually it would reach the threshold where it's performance is not enough to keep up.