bully for you :)

the “guardrails” they mention. They are a bunch of if/then statements looking to work around methods that the developers have found to produce undesirable outputs. It doesn’t ever mean “the llm will not bo doing this again”. It means “the llm wont do this when it is asked in this particular way”, which always leaves the path open for “jailbreaking”. Because you will almost always be able to ask a differnt way that the devs (of the guardrails, they don’t have much control over the llm itself) did not anticipate.

Expert systems were kind of “if we keep adding if/then statements, we would eventually cover all the bases and get a smart, reliable system”. That didn’t work then. It won’t work now either

yes, “complex” regexes are quite simple too. Complex regexes are long, not difficult. They appear complex because you have to “inline” everything. They really are not that hard.

always read the news before updates. There was one that said manual intervention was needed, and gave you the exact command you needed to run

I would support them joining. But of course no fucking tantrums will be tolerated. You will abide by the same rules as everyone else.

Don’t. It’s a horrible overheating piece of crap. I literally cannot shoot more than about 3 minutes of video with the flash turned on (at 1080p, not 4k, and not encoding as hevc either). The phone overheats and turns off the flash.

Keeping the phone in my pocket, out of direct sunlight in my car? I see the “3d buildings have been disabled because your phone needs to cool down” every single day. And I live in Malta; in the summer it’s a 20 minute trip, at most.

And even then, the battery life sucks anyway.

Android 16 is buggy af too, though that’s not specific to the 7a.

does the regex search for what you wanted to? Does it work in all cases? Can I be confident that it will find all instances i care about, or will I still have to comb the code manually?

tests can never prove correctness of code. All they can prove is “the thing hasn’t failed yet”. Proper reasoning is always needed if you want a guarantee.

If you had the llm write the regex for you, I can practically guarantee that you won’t think of, and write tests for, all the edge cases.

that would be more believable if they didn’t release the apple vision pro.

Or the years they took biding their time before they finally implemented battery charge time estimation on ios.

Or the time biding their time refining, erm, copy and paste?

Come on!

and the only reason it’s not slowing you down on other things is that you don’t know enough about those other things to recognize all the stuff you need to fix

by special casing a lot of things. Like expert systems, in the 80s

yes they can. I regularly do. Regexes aren’t hard to write, their logic is quite simple. They’re hard to read, yes, but they are almost always one-offs (ex, substitutions in nvim).

1% slowdown is pretty bad. You’d still do better just not using it. 19% is huge!

no, they aren’t processing high quality data from multiple sources. They’re giving you a statistical average of that data. They will always be wrong by nature. Hallucinations cannot be eliminated. Anyone saying otherwise (irrelevant of how rich they are) is bullshitting.

these types of laws usually come from the most technically illiterate people ever

yep. you could of course swap weights in and out, but that would slow things down to a crawl. So they get lots of vram (edit: for example, an H100 has 80gb of vram)

that’s why they need huge datacenters and thousands of GPUs. And, pretty soon, dedicated power plants. It is insane just how wasteful this all is.

yes, but that doesn’t help if the software refuses to run on modern java

i wasn’t born yet. I don’t even think half of me was in my dad’s balls yet

imagine that to type one letter, you need to manually read all unicode code points several thousand times. When you’re done, you select one letter to type.

Then you start rereading all unicode code points again for thousands of times again, for the next letter.

That’s how llms work. When they say 175 billion parameters, it means at least that many calculations per token it generates