HansHamster

No, that was directly from deepseek. And it happened very consistently (3 or 4 times in a row, clean session every time, and across 2 harnesses). Guess I'll give it another try when v4.1 flash is available.

I must be doing something wrong. I gave v4 pro a try a couple of days ago, gave it a simple prompt like "clean up functions x and y in file z" and it would always start off promising, just to quickly get sidetracked, start hallucinating problems in the code, and just get stuck for hours until I interrupt it:

— hmm — 0x2D696370 — little-endian bytes: 70 63 69 2D = 'p','c','i','-' — hmm — WAIT — WAIT — !!!!! — *WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — *HOLD ON — HOLD ON — HOLD ON — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — !!!!!!!! — *WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — *OK — WAIT — I THINK I FINALLY SEE THE WHOLE PICTURE — I NEVER READ IT — AND — THE LAYOUT — hmm — !!!!! — *WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — WAIT — HOLD ON — HOLD ON — HOLD ON — HOLD ON

Then gave the same to Sonnet 5 and it was done 15 - 30 minutes later. I tried v4 pro both in claude code and codewhale with similar results. Haven't tried the new deepseek harness.

Yeah, I'm still concerned about crystalline entities suddenly showing up. Have they ever fixed it? I don't see anything in the issue tracker, probably because no one was left last time to report it...

Maybe their CRTs had horrible burn-in and they had to erase everything 9 times before it was gone...

I would expect all RNG algorithms to be deterministic and stable with their seed, but the cryptographically secure ones to have some additional properties like making it unfeasible to reverse the seed from the output, having a very long period or strong guarantees on the distribution of the output. It's just that using a 'secure' algorithm is often overkill for a game when you don't really need those extra guarantees.

It feels a bit unfair to say that it is faster by being able to tell the total length from the first byte and capping it at 64 bit, while some of the other formats can store arbitrarily large integers. I guess you could use another variable length encoding for the prefix at the cost of some performance and using even more space...

Eh... unfortunately they shut down their forums a couple of years ago. So good luck getting any form of support as a free user even if you run into real bugs in their software (believe me, I tried...)

That being said, I have used their ice40 and ECP5 FPGAs with Yosys for a couple of small projects and that worked perfectly fine.

bacon!

Clearly, we should place a radioactive source, a Geiger counter, and a computer in a sealed box. Every time the counter registers a decay, the computer performs a HTTP GET. Thus, we end up with Schrödinger's webserver...

At least you can tick the "stay signed in" checkbox and... get kicked out a few hours later with a smug "you successfully signed out" message.

> which is faithfully translated by the (hopefully bug-free) compiler.

"Hey Claude, translate this piece of PHP code into Power10 assembly!"

> You have to be the one who reaches out.

But that's the whole issue. Who am I supposed to reach out to? The 2 people at work I occasionally talk to because they happen to sit in the same office as me?