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

oh no...not again...;)

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.

I was puzzled too. Maybe there is (or was) a probationary period?

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

This is novella erasure.

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

Naturally, it is however noticeable that in the lead up to a model release we always get massively degraded performance for the preceeding few weeks

It's been like that for each model release within the last year

but how true is this? this is almost impossible to measure and those that do[1] find no significant difference

i personally haven't noticed any downgrade at all.

it's entirely possible there's a mass delusion going on where everyone gets wowed by 4.6 initially, then accepts the new baseline and gets used to it, then thinks that baseline is no longer impressive and thus degraded

it doesn't help that anthropic changed defaults for its claude code harness for all users suddenly

the best and only evidence i've seen for actual degradation is that the web version of opus 4.6 failed the car wash test, and since you cannot simply choose to "disable adaptive thinking" and other parameters with the web version, you truly may have gotten a worse product

[1] https://marginlab.ai/trackers/claude-code-historical-perform...

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/