Hacker News: ntonozzi

New comment by ntonozzi in "Disney erased FiveThirtyEight"

ntonozzi — Tue, 19 May 2026 20:43:29 +0000

Everyone said that except for 538. That's why 538 was worth reading.

New comment by ntonozzi in "Welcome to FastMCP"

ntonozzi — Tue, 24 Mar 2026 22:30:33 +0000

Something like Cloudflare's Code Mode fixes both of these! No privileged bash environment, no VM necessary, no exposing credentials to the LLM.

As the article states, LLMs are fantastic at writing code, and not so good at issuing tool calls.

New comment by ntonozzi in "The bureaucracy blocking the chance at a cure"

ntonozzi — Mon, 16 Mar 2026 22:27:46 +0000

The UK is begging for people to build datacenters: https://www.theguardian.com/technology/2026/mar/09/revealed-...

New comment by ntonozzi in "Polymarket gamblers threaten to kill me over Iran missile story"

ntonozzi — Mon, 16 Mar 2026 16:38:30 +0000

Perhaps because he is a journalist whose job is to report reality, not avoid threats?

New comment by ntonozzi in "Surpassing vLLM with a Generated Inference Stack"

ntonozzi — Fri, 13 Mar 2026 21:02:01 +0000

Yeah you can: https://thinkingmachines.ai/blog/defeating-nondeterminism-in....

New comment by ntonozzi in "Surpassing vLLM with a Generated Inference Stack"

ntonozzi — Tue, 10 Mar 2026 18:55:18 +0000

Why do they need to run benchmarks to confirm performance? Can't they run an example prompt and verify they get the exact same output token probabilities for all prompts? The fact that they are not doing this makes me suspicious that they are in fact not doing the exact same thing as vLLM.

It is also a bit weird that they are not incorporating speculative decoding, that seems like a critical performance optimization, especially for decode heavy workloads.

New comment by ntonozzi in "A GitHub Issue Title Compromised 4k Developer Machines"

ntonozzi — Thu, 05 Mar 2026 21:50:14 +0000

IMO the core of the issue is the awful Github Actions Cache design. Look at the recommendations to avoid an attack by this extremely pernicious malware proof of concept: https://github.com/AdnaneKhan/Cacheract?tab=readme-ov-file#g.... How easy is it to mess this up when designing an action?

The LLM is a cute way to carry out this vulnerability, but in fact it's very easy to get code execution and poison a cache without LLMs, for example when executing code in the context of a unit test.

New comment by ntonozzi in "A case for Go as the best language for AI agents"

ntonozzi — Mon, 02 Mar 2026 20:15:01 +0000

Wow that is wild, that is exactly along the lines of my fantasy language. It'd be so easy to go into the deep end building tooling and improving a language like this.

New comment by ntonozzi in "OpenClaw is basically a cascade of LLMs in prime position to mess stuff up"

ntonozzi — Tue, 03 Feb 2026 22:41:44 +0000

That argument was dead _at least_ 2 years ago, when we gave LLMs tools.

New comment by ntonozzi in "The challenges of soft delete"

ntonozzi — Tue, 20 Jan 2026 23:42:07 +0000

Many privacy regulations enforce full deletion of data, including GDPR: https://gdpr-info.eu/.

New comment by ntonozzi in "The challenges of soft delete"

ntonozzi — Tue, 20 Jan 2026 23:32:18 +0000

I've given up on soft delete -- the nail in the coffin for me was my customers' legal requirements that data is fully deleted, not archived. It never worked that well anyways. I never had a successful restore from a large set of soft-deleted rows.

New comment by ntonozzi in "Apple picks Gemini to power Siri"

ntonozzi — Mon, 12 Jan 2026 16:16:21 +0000

Hopefully it gets more tightly integrated.

New comment by ntonozzi in "US will ban Wall Street investors from buying single-family homes"

ntonozzi — Wed, 07 Jan 2026 23:47:59 +0000

Home affordability is getting better anyways, which is great, because we are finally having a surge in new & denser home building in popular regions and there mortgage rates are more reasonable than they were in the COVID-era.

New comment by ntonozzi in "US will ban Wall Street investors from buying single-family homes"

ntonozzi — Wed, 07 Jan 2026 20:19:53 +0000

Maybe the best part of this legislation will be that people will realize it's not institutional investors that are driving up home prices. No, that's far too optimistic.

New comment by ntonozzi in "Show HN: Safe-NPM – only install packages that are +90 days old"

ntonozzi — Wed, 26 Nov 2025 21:55:35 +0000

It's not debouncing, it's delaying. Ideally you can still update a specific dependency to a more up to date version if it turns out an old version has a vulnerability.

New comment by ntonozzi in "Solving Fizz Buzz with Cosines"

ntonozzi — Fri, 21 Nov 2025 22:55:45 +0000

One of my favorite blog posts of all time: https://aphyr.com/posts/342-typing-the-technical-interview

New comment by ntonozzi in "CBP is monitoring US drivers and detaining those with suspicious travel patterns"

ntonozzi — Thu, 20 Nov 2025 23:03:09 +0000

There are some good reasons it is lower now, like defense lawyers and Miranda rights. Obviously it'd be good if we had both good civil rights AND high murder clearance, but they seem in obvious tension with each other.

New comment by ntonozzi in "Building more with GPT-5.1-Codex-Max"

ntonozzi — Wed, 19 Nov 2025 18:31:25 +0000

If you haven't, give Cursor's Composer model a shot. It might not be quite as good as the top models, but in my experience it's almost as good, and the lightning fast feedback is more than worth the tradeoff. You can give it a task, wait ten seconds, and evaluate the results. It's quite common for it to not be good enough, but no worse than Sonnet, and if it doesn't work you just wasted 30 seconds instead of 10 minutes.

New comment by ntonozzi in "The Department of War just shot the accountants and opted for speed"

ntonozzi — Wed, 12 Nov 2025 19:08:02 +0000

My question is genuine.

Not really the point, but an idea that springs to mind is selling fighter jets to allied countries.

New comment by ntonozzi in "AI is Dunning-Kruger as a service"

ntonozzi — Wed, 12 Nov 2025 18:20:14 +0000

Check out this graphic:

https://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect#...

This is the only thing Dunning-Kruger found.

Actual performance is correlated with perceived performance, mediated by the fact that everyone thinks they are a bit above average.