That’s why I’m here

Being needlessly confrontational will do that. But anyway, watch the short, it was surprisingly good.

That was the joke

Reported, rule 5

I have not been paying attention to threads and so I gave it a quick google. It seems that threads is doing just fine, with 130 million monthly users now.

Where should I be looking for the grisly stats?

“elections”

Huh, turns out this stuff is pretty complicated. Should have known 😛

Maybe they could allow links to stories about the US which are from foreign news outlets. E.g. US bombing in yemen:

BBC

Al Jazeera

DW

Give an alternative a go, see if you have better luck. There’s adguard home, blocky, and Technitium DNS for you to consider.

Alternatively, the window trick should work.

I think that happened 8 years ago or so

Being over Russian airspace was the stupid move here.

Thank you for sharing your expertise, you’ve given me lots to Google :)

I wish I too knew enough about coins to date coins on a thumbnail.

What kind of coin is it, and what dates it to ~3rd century ad?

Let me expand a little bit.

Ultimately the models come down to predicting the next token in a sequence. Tokens for a language model can be words, characters, or more frequently, character combinations. For example, the word “Lemmy” would be “lem” + “my”.

So let’s give our model the prompt “my favorite website is”

It will then predict the most likely token and add it into the input to build together a cohesive answer. This is where the T in GPT comes in, it will output a vector of probabilities.

“My favorite website is”

"My favorite website is "

“My favorite website is lem”

“My favorite website is lemmy”

“My favorite website is lemmy.”

“My favorite website is lemmy.org”

Woah what happened there? That’s not (currently) a real website. Finding out exactly why the last token was org, which resulted in hallucinating a fictitious website is basically impossible. The model might not have been trained long enough, the model might have been trained too long, there might be insufficient data in the particular token space, there might be polluted training data, etc. These models are massive and so determine why it’s incorrect in this case is tough.

But fundamentally, it made up the first half too, we just like the output. Tomorrow some one might register lemmy.org, and now it’s not a hallucination anymore.

Very difficult, it’s one of those “it’s a feature not a bug” things.

By design, our current LLMs hallucinate everything. The secret sauce these big companies add is getting them to hallucinate correct information.

When the models get it right, it’s intelligence, when they get it wrong, it’s a hallucination.

In order to fix the problem, someone needs to discover an entirely new architecture, which is entirely conceivable, but the timing is unpredictable, as it requires a fundamentally different approach.

Wat

Those are rookie numbers, gotta pump them up!

How many charges is he currently facing? I feel like every few days there’s another indictment.

I will cut off your Johnson!

Just waiting patiently for boost.