Neywiny

The MP1 is 7.5 years old now.

Imagine being less character efficient just to be a bigot. Hope you stocked up on RAM for all that extra text

Booooooooooo

I think you mean "despite the STM32 in the product name, they're 64 bit compatible cores." Because STM8 was 8 bit (though I've never seen one in any design ever, I'm sure they're just before my time) and STM32 MCUs and MPUs were always 32-bit.

I'm worried they dug too deep a trench with the 32. Like how do much from Espressif is an ESP32 now despite them ranging from slower single core to faster dual core, now even with mmu, some with Wi-Fi some not...

What is in a name?

I won't link it because idk seems toxic but the last one who replied started with "It's pretty tedious to compare" about their slopcode. To be too lazy to ask the LLM to put that in too is incredible

I have no use for this but I want to commend you on defending your claims and taking objective numeric measurements. The lack of these lately on performance improvement based projects has been disturbing

I still can't imagine hooking up an LLM to real hardware because of exactly this.

This is perfect. Real programming has a ton of these instances of minor changes.

They keep talking about 2 accounts logged in so that's why it's still high. But they've done nothing to defend that claim.

Also, pro tip, you can still just use it in browser. I hope that doesn't go away.

I mean what'll you do? Intel only for PCs? Like in disappointed too but I'm not gonna go try to fab the stuff myself.

Pathological liar says thing. More at 11

You can simulate it communicating with satellites in the chamber. Especially since if they're at X or Ku band, and coil whine is in the audible range, it really shouldn't interfere with the measurement?

I mean I guess but the readme made it sound like this would be a night and day difference. A lot of bashing of the original.

Without seeing the memory saving metric and error bars, these are marginal improvements. Kudos on making a thing but I'm not seeing it. I also don't have a 68k mac though so maybe I don't see this being a big deal.

Source they didn't train on it?

So disappointing to see no direct numeric comparisons with the original.

The US can. There are domestic packaging people and board houses. I think the EU can but I'm not sure and that's not a country.

If it was about wine, why would I want one with a training data cutoff? I'd much rather have one that can query a database about wine

I feel like this is a dumb question, but why are we spending any effort on wine comparisons? Is there a way to get rid of experts on these to just be ones for code?

Minor investors. Semi-major. Everybody

3 ultra vs 3.5 super is a big discussion. But in mine and others' experiences, 3.5 super is a lot worse than 3 ultra.

Yeah I'm giving all my RAM to Sam Altman tomorrow because of that

While true, I tried it devcontainers recently for the first time and it was molasses slow for every keystroke in the terminal and action with files. Ended up putting dropbear in the container temporarily and sshing into it using the standard remote connection. That got it back to normal. I should see about filing a GitHub issue ticket

I think it's mostly a testing thing. Valgrind is a friend a lot of people haven't heard of for c/c++. Setting up good regression tests is an art. Maintaining them is even harder.

It's not about your clock speed, it's about your edge rate. Anyone who's had to lower drive strength or slew rate can tell you that even at 0.0000...1 Hz clock speed, if your routing is trash it can ring to the point of detecting multiple edges or interfering with other signals.

Also some of the issues were on USB lines which hopefully aren't running at 2MHz.

Lastly, since you're coding it, maybe make it pull reference layouts+routing for power supplies from the datasheets. That's step 1 for any real eCAD student.

No explanation of why checking their charge causes a spike in power? To me that's weird but somehow accepted as normal

I have 96GB of good RAM. I bought it around this time 3 years ago. Up around 550% when I checked the other day. If a stick dies, it dies. Very sad

Just occurred to me that Amazon seems interestingly positioned relative to the book sourcing thing. I guess that's still not enough.

I think this is true of any trained anything. It's the fish climbing a tree scenario. The teens on Ellen getting laughed at for not knowing how to fold a paper map.

There's infinite front end code to train on. Virtually infinite python and shell scripts too. As I've worked my way away from such domains, the LLM outputs have gotten worse. It just makes sense.

Yeah but that was because it was gently asked to please not. I mean running a firewall/proxy that actually does it.