utopcell

You probably mean absl::flat_hash_map<>.

Many security tools for doing security audits with LLMs are based around a "look at this file" loop

This makes sense. At most it converts the question of ability to a question of cost (i.e. fire up a prompt for each file).

This article reduces the hype about Mythos in my mind: A new model that can find 9 new bugs while no previous model can identify them, is a whole different story from what this article demonstrates: that only 2/9 of the detected bugs are new for Mythos.

Great work.

You can see which bugs each model found in the full report.

This should have probably been surfaced at the text. To answer my own question: If one uses gemma4-26b-a4b, mimo-v2.5-pro and gemini-3.5-flash then 7/9 bugs are covered, while no model can uncover the remaining two.

And, you have misunderstood what the benchmark does. It tells the model to audit the file, and it is allowed to look at the rest of the repo. It is not pointed at the bug.

I obviously meant that the model was pointed to the bug report. What would have been the point of providing the actual bug. This is still easier than telling Mythos to generally look at a codebase and find any bug.

Id soft folks were using 2 graphics cards, an EGA/VGA and an MDA one to do multihead debugging. It was possible because the two card technologies actually mapped their frame buffers onto two separate address ranges. Cool stuff.

"Every mathematician wants to discover a mathematician's lemma."

It might have been easy to guess, but you didn't really think of it in the past 51 years since the Commodore 128 was introduced, did you?

The "best" model finds 4/9 bugs. It would be interesting to see if all models find the _same_ bugs. Does a collection of models exist that can cover all 9?

Also, it seems to me that pointing a model to a bug and asking it to solve it is somewhat easier than what Mythos did, which if I understand correctly, was to generally look at a codebase and find any bug. Even so, non-Mythos models only managed to fix 4/9 of these bugs.

I think the article makes the point that Mythos is at a different level.

thanks for keeping us honest. what would we ever do without this insightful comment of yours?

not really solving the problem though. would be easier to directly search for project euler xx solution.

After looking at this enormous labor of love, is this really what you chose to comment about?

Gold medal @ the 2025 International Math Olympiad.

neat!

This article is from Jan 8.

The Q10 has been my daily driver for years, great keyboard. I see that they're coming out with a split alice [1] though sadly it seems it is only for the Chinese market

[1] https://www.guru3d.com/story/keychron-launches-z11-ultra-8k-...

I see your point, though strictly speaking, the two products I mentioned mimic 12AX7 tubes, which are preamp tubes. I'm not aware of E2E designs that also mimic power tubes.

Minor correction:

An experienced guitarist cannot distinguish between "captured" amps, or amps which at their core simulate vacuum tubes at the software level. I definitely can't tell the two apart. However, I believe it is easy to distinguish a pure vacuum tube-based circuit from a JFET/MOSFET-based one.

There do exist vacuum tube replacements like the AMT 12AX7WS [1] or Jet City's RetroVales [2], but I would argue that the fact that they try to emulate tubes via transistors is a strong indicator that the natural circuits for both sound distinct enough for guitarists.

[1] https://amtelectronics.com/new/amt-12ax7ws/

[2] https://web.archive.org/web/20190803060713/http://www.robert...

Sup-par phrasing is a subtle advantage of non-AI generated text. In the past, I would be put off by this bad phrasing and the typo ("requier") in the text, but these days, it's a signal that a human took the time to write this, which makes me happy to see.

..or is it "sub-par"?

Layoffs might not be the best way to keep talent. Imo, Nintendo did it best back in 2014 [1].

[1] https://www.nintendolife.com/news/2014/01/iwata_and_miyamoto...

After all these years, I still think that this was a wasted opportunity on Google's side. As is well-known, Google (Googol) is a constant: 10^100. Instead of Alphabet, they should have named the umbrella company AlephBet [1] with a tag line: "we stopped thinking in constants".

[1] https://en.wikipedia.org/wiki/Aleph_number

Alphabet was Warren Buffet's last "hold" pick afterall.

Rp2040 has a usb 1.1 port. It doesn't have the bw for 192khz.

Someone should add a grid of mics and speakers inside a keyboard to record impulse responses for different kinds of keys. In this way, one can first do noise cancellation for the currently used keys, and then apply an IR to make the keyboard sound like another one.

what profit?

"Completely unusable" is an over-exaggeration. By default, assume good will.

I wonder: Is a resurface of "The Last Question" ever complete without mentioning "Universal Paperclips" [1]?

[1] https://www.decisionproblem.com/paperclips/index2.html

This is not an alternative source for the comic, it's a whole different comic. Cool!

In 1955, he was promoted to tenured associate professor. In December 1957, Asimov was dismissed from his teaching post, with effect from June 30, 1958, due to his lack of research.

I thought the whole point of getting tenure is that you can't get fired.

Good. So we have a super short story and a short story. Someone should write a book now.

Mythos is speculated to have 10 trillion parameters. Almost certainly they were training it for months.

This is the real Litmus test isn't it? There will be a deafening silence from critics when AI decides P vs NP.

It's a Delphi-compatible IDE: https://www.lazarus-ide.org/