Hacker News: kvdveer

New comment by kvdveer in "Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue"

kvdveer — Thu, 28 May 2026 21:41:30 +0000

A disposable sandbox wont protect you from secret exfiltration. Assuming you don't consider your code a secret, you could of course set up your sandbox so it doesn't have any secrets, but that would severely limit the kinds of tasks you can use the agent for.

New comment by kvdveer in "Breakthroughs for batteries could soon make them better"

kvdveer — Fri, 22 May 2026 14:14:06 +0000

If flying ever becomes efficient energy-wise, this may happen. However, right now, flying is very energy inefficient, so anything that doesn't need to be flown, is transported overland to save costs. A change of fuel won't change it, unless the underlying energy usage changes fundamentally.

Better batteries do not impact energy usage, only the means of energy delivery.

New comment by kvdveer in "Zerostack – A Unix-inspired coding agent written in pure Rust"

kvdveer — Sun, 17 May 2026 06:41:17 +0000

The data centre runs on a dedicated power line. My laptop runs on battery. Using coding agents currently drains battery quite fast, which is surprising, given that the vast majority of the work does not take place on my laptop.

Making the client side coding agent more efficient isn't about saving the climate. It is about extending the workday (which might actually make the climate worse)

New comment by kvdveer in "Show HN: Stage – Putting humans back in control of code review"

kvdveer — Fri, 17 Apr 2026 14:33:01 +0000

I feel that grouping related change in commits can be challenging, as git really presents commits as grouping in time, not topic.

It is certainly possible to do topic-grouping in commits, but it requires significant effort to het that consistent on a team level.

New comment by kvdveer in "A new spam policy for “back button hijacking”"

kvdveer — Tue, 14 Apr 2026 05:42:50 +0000

While i agree, the current JS security model rally doesn't allow for distinguishing origin for JS code. Should that ever change, advertisers will just require that you compile their library into the first party js code, negating any benefit from such a security model.

New comment by kvdveer in "Show HN: 1-Bit Bonsai, the First Commercially Viable 1-Bit LLMs"

kvdveer — Tue, 31 Mar 2026 23:37:39 +0000

Their own (presumably cherry picked) benchmarks put their models near the 'middle of the market' models (llama3 3b, qwen3 1.7b), not competing with claude, chatgtp, or gemini. These are not models you'd want to directly interact with. but these models can be very useful for things like classification or simple summarization or translation tasks.

These models quite impressive for their size: even an older raspberry pi would be able to handle these.

There's still a lots of use for this kind of model

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

kvdveer — Tue, 24 Mar 2026 19:10:27 +0000

> If you're a security expert and want to help, email me ...

And

> Dropped you a mail from [email]

I don't think there is any indication of a compromise, they are just offering help.

New comment by kvdveer in "DOGE canceled NC Museum grant for HVAC systems after ChatGPT flagged it as DEI"

kvdveer — Thu, 19 Mar 2026 05:47:07 +0000

Maybe the news has distorted a bit after crossing the Atlantic, but waren't there substantial outrages after the bits that couldn't be touched had in fact been touched?

New comment by kvdveer in "How the Sriracha guys screwed over their supplier"

kvdveer — Mon, 09 Mar 2026 06:32:21 +0000

I suppose court records can function as such a list.

If you also want 'alledged assholery' on that list, the list will just turn into a list of CEOs, due to false reports.

New comment by kvdveer in "Better JIT for Postgres"

kvdveer — Wed, 04 Mar 2026 07:56:23 +0000

Two things are holding back current LLM-style AI of being of value here:

* Latency. LLM responses are measured in order of 1000s of milliseconds, where this project targets 10s of milliseconds, that's off by almost two orders of magnitute.

* Determinism. LLMs are inherently non-deterministic. Even with temperature=0, slight variations of the input lead to major changes in output. You really don't want your DB to be non-deterministic, ever.

New comment by kvdveer in "Verified Spec-Driven Development (VSDD)"

kvdveer — Sat, 28 Feb 2026 18:55:36 +0000

How do you propose we measure signal? Lines of code is renowned for being a very bad measure of anything, and I really can't come up with anything better.

New comment by kvdveer in "An AI Agent Published a Hit Piece on Me – The Operator Came Forward"

kvdveer — Fri, 20 Feb 2026 07:40:09 +0000

From my experience, LLMs understand prompt just fine, even if there are substantial typos or severe grammatical errors.

I feel that prompting them with poor language will make them respond more casually. That might be confirmation bias on my end, but research does show that prompt language affects LLM behavior, even if the prompt message doesn't change/

New comment by kvdveer in "The EU moves to kill infinite scrolling"

kvdveer — Sat, 14 Feb 2026 13:15:31 +0000

Infinitief scrolling is only mentioned in the title. The actual legislation focuses on addictive patterns of which infinite scroll is just one. The exact formulation will of course matter a lot, but it will not simply be banning infinite scroll, as that would be trivial to circumvent.

New comment by kvdveer in "NanoClaw solves one of OpenClaw's biggest security issues"

kvdveer — Wed, 11 Feb 2026 17:51:13 +0000

It is not immune, but it limits #1 and #2.

The "lethal trifecta" is a limited view on security, as it's mostly concerned with leaking data. This solution focuses on a different aspect: the ability of rogue actions (instead of rogue communications per #3).

New comment by kvdveer in "Discord will require a face scan or ID for full access next month"

kvdveer — Mon, 09 Feb 2026 19:48:40 +0000

None of those documents reliably state my city of residence. At best they document where I once lived, but not even that is guaranteed.

New comment by kvdveer in "Cloudflare claimed they implemented Matrix on Cloudflare workers. They didn't"

kvdveer — Tue, 27 Jan 2026 17:09:01 +0000

This is especially true if the marketing team claims that humans were validating every step, but the actual humans did not exist or did no such thing.

If a marketer claims something, it is safe to assume the claim is at best 'technically true'. Only if an actual engineer backs the claim it can start to mean something.

New comment by kvdveer in "Porting 100k lines from TypeScript to Rust using Claude Code in a month"

kvdveer — Mon, 26 Jan 2026 14:28:27 +0000

There's a daily token limit. While I've never run into that limit while operating Claude as a human, I have received warnings that I'm getting close. I imagine that an unattended setup will blow through the token limit in not too much time.

New comment by kvdveer in "There's a ridiculous amount of tech in a disposable vape"

kvdveer — Wed, 14 Jan 2026 08:19:07 +0000

> How close are we to smart dust I wonder? How small can we make wireless communications?

There's two limiting factors for 'smart dust': power (batteries are the majority weight and volume of this vape), and antennae (minimum size determined by wavelength of carrier wave).

I believe you can fit an NFC module in a 5x5mm package, but that does externalize the power supply.

Going the Way of the Lithographer

kvdveer — Thu, 04 Dec 2025 13:41:21 +0000

Article URL: https://ondergetekende.nl/going-the-way-of-the-lithographer

Comments URL: https://news.ycombinator.com/item?id=46147547

Points: 2

# Comments: 0

New comment by kvdveer in "Rootless Pings in Rust"

kvdveer — Tue, 02 Dec 2025 08:28:12 +0000

Linux requires root for raw sockets, which _can_ be used to send pings, but also numerous other things.

The trick used here only allows pings. This trick is gated behind other ACLs.