HackerTrans
トップ新着トレンドコメント過去質問紹介求人

kvdveer

no profile record

投稿

Going the Way of the Lithographer

ondergetekende.nl
2 ポイント·投稿者 kvdveer·7 か月前·0 コメント

コメント

kvdveer
·17 日前·議論
The added value of the LLM here is probably zero. Just type a search propmt in a search engine. If the top 5 results don't cover the same ground your article is covering, at the very least, your article will expose new knowledge to people using that search term.

Typing up LLM instructions and reading the output is probably more work.
kvdveer
·20 日前·議論
What would be the incentive for site owners to reduce the appeal of their site? The user has connected to the site, so there's obviously no immediate problem.
kvdveer
·25 日前·議論
In the video you can see that the LED lights the logo less evenly than the EL lighting. While that's not important at all, this might be the reason behind this odd choice
kvdveer
·先月·議論
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.
kvdveer
·2 か月前·議論
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.
kvdveer
·2 か月前·議論
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)
kvdveer
·3 か月前·議論
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.
kvdveer
·3 か月前·議論
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.
kvdveer
·3 か月前·議論
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
kvdveer
·4 か月前·議論
> 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.
kvdveer
·4 か月前·議論
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?
kvdveer
·4 か月前·議論
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.
kvdveer
·4 か月前·議論
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.
kvdveer
·4 か月前·議論
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.
kvdveer
·5 か月前·議論
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/
kvdveer
·5 か月前·議論
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.
kvdveer
·5 か月前·議論
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).
kvdveer
·5 か月前·議論
None of those documents reliably state my city of residence. At best they document where I once lived, but not even that is guaranteed.
kvdveer
·6 か月前·議論
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.
kvdveer
·6 か月前·議論
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.