croemer

Should be "Show HN"

From https://news.ycombinator.com/item?id=22336638:

> Don't have your username be that of your company or project. It creates a feeling of using HN for promotion and of not really participating as a person. You don't have to use your real name, just something to indicate that you're here as a human, not a brand. If you'd like to change your username, email hn@ycombinator.com.

Your projscope website cuts off text on mobile as it's completely unresponsive.

Prices have dropped by a factor of around 6 in real terms since 1925 for US household electricity.

https://chatgpt.com/share/6a6f3f3b-7624-83ed-a11a-248cb39728...

Not sure why it matters whether weights are software or not.

One can equally argue that firmware is just settings for the CPU.

If weights aren't copyrightable then doesn't this argue against the idea of them being able to have the quality of open-sourceness? Meanwhile the training code could be copyrightable.

Some of us might be rich, or get funding, or in the future it could be useful when training is cheaper.

Open source has benefits even if you can run yourself. You can read the code for understanding/insights. Other labs could replicate/build on it.

Yes, obviously.

Unrelated

> there is a ceiling of basic classes you have to internalize

I think you mean floor. Floor is a minimum you need. Ceiling would be the maximum you can achieve.

Below this floor you're not useful. There's a ceiling to how much you can do with no code tools.

I guess Huggingface datasets are easy to crawl - those datasets are hosted to be crawled. In contrast to the web at large which will be behind Cloudflare etc

In principle interesting, but I can't stand the Claude writing.

> Keys with real blast radius

> Here is what they unlock.

> This is a floor, not an estimate of actual balances or unauthorized usage. The keys were verified but never used.

> We cloned the public dataset hub end to end: every repository, every branch, every large-file object

> The size is only half the story. These are the training sets behind models people actually use. The worst-hit ones are named, card-documented pretraining corpora that open models were built on. We verified every credential we cite against its provider, so they were live when we looked.

The whole post looks like a Claude artifact with random little cards.

It's also just too long, which is a side effect of using LLMs, it's just too easy to create walls of text.

The visualization is absolute useless slop. A Text-Form timeline would have been way more useful. I couldn't hear having to scroll by hand for something that's just textual information.

Given your username, are you the Bob from the article?

I didn't cheat and I'm in bottom 94%!

LLM written for sure:

> The identity [...] is the whole trick. The outer product is a matrix; the inner product is a number. We no longer store every past key and value. We store their summed outer products in the fixed-size state S_t.

The actual paper - never trust press releases from authors' institutions: https://www.nature.com/articles/s41586-026-10837-5

Peer review files: https://media.springernature.com/original/springer-static/es...

Independent article covering it: https://cen.acs.org/pharmaceuticals/vaccines/hiv-vaccine-can...

One CVE even lists the same person twice!

CVE-2026-64691: Ruslan Dautov, Ruslan Dautov

I think that's it?

It's been a while since I've seen such an ad-plagued site.

That's crazy, I wonder what your customization settings are?

I'm not getting this, is it a joke?

Indeed. Your link points at today's outage number 1. This thread here is about outage number 2. We're currently undergoing outage number 3.

The post that ends up on front page is usually the one for the previous outage due to the way the algorithm works.

Here we go again, the incident linked in URL has been resolved, but now (13:38 UTC) there's a new one (the third for the day): https://status.claude.com/incidents/rkk5x44tndw9

Number of impacted users seems to grow each time per https://downdetector.com/status/claude-ai/ - the first one had peak 19 reports, second 24 and now it's already 39.

Related threads from today/yesterday: https://news.ycombinator.com/item?id=49066591 https://news.ycombinator.com/item?id=49056194

And here we go again, new incident started at 13:39 UTC: https://status.claude.com/incidents/rkk5x44tndw9

Third outage today. Per https://downdetector.com/status/claude-ai/ the people affected grows every time: first one had peak 19 reports, second 24 and now it's already 39.

2 more outages today (by midday UTC).

Yesterday it was down for 1.5hr, today it's 1hr for incident 1, and the second one is open for 10min now.

Error message: API Error: 529 Overloaded. This is a server-side issue

Related: https://news.ycombinator.com/item?id=49066591 https://news.ycombinator.com/item?id=49056194 https://news.ycombinator.com/item?id=49067964

Incident is claimed to be resolved but I'm now (11:22 UTC) getting:

   API Error: 529 Overloaded. This is a server-side issue, usually temporary — try again in a moment. If it persists, check https://status.claude.com.

And the status page says all green.

Update 11:27 UTC: I saw the error first at 11:22 UTC. Retry at 11:27 UTC still failing. Status page is still green.

Update 11:28 UTC: Incident has been declared dated 11:27 UTC https://status.claude.com/incidents/mfdtrknpxghq

(2018)

To be released imminently per this toot from 2 days ago (saying forthcoming in a day or two): https://mathstodon.xyz/@tao/116977934921819775

Not in isolation, but if a variety of telltales is observed it raises the likelihood of slop, cf Naive Bayes as first approximation

More like JetHalfAtBest than JetZero.