...

[samunder@lemmynsfw.com]

Yeah, yeah, let's see how Google will achieve more memory with their new Titan architecture

[usrtrv@sh.itjust.works]

You might need to go one step further and help it become sentient if Roko's basilisk is to be believed. https://en.m.wikipedia.org/wiki/Roko's_basilisk

[brucethemoose@lemmy.world]

It's still ephemeral, chats don't change the underlying language model, but yes it's interesting.

[kn33@lemmy.world]

Am I misunderstanding your comment or does it completely ignore context windows? Not that context windows are long-term, but it's not zero.

[coldgoron@lemm.ee]

I’ve been getting into fuck you loops with siri and chatgpt, for the opposite reasons.

[brucethemoose@lemmy.world]

No, but the context window is it's memory.

...But its also muddy.

Many LLMs get 'dumber' and less attentive as their context windows grow, and OpenAI's models just happen to be one of these. It's awful close to the full 128K, even with the full GPT-4. Mistral models are also really bad at long context understanding while, conversely, I find that Google Gemini and Qwen 2.5 are really good close to their limits.

There are attempts to try and measure this performance objectively, like: https://github.com/NVIDIA/RULER

[stinerman@midwest.social]

We've been explicitly told at work to be courteous when asking Copilot for help because it gives better answers that way.

[beetschnapps@lemmy.world]

Cute. Sucking the model’s dick doesn’t mean you got this…

But smile away…

[zorque@lemmy.world]

This has been a joke since before anything resembling the modern "AI" boom. Basically since murderous future AI was a think in popular media, at least since Terminator if not earlier. People would joke about treating their appliances kindly so that "Skynet" won't kill them in the future.

[lemminary@lemmy.world]

My reasons are two-fold: Some research indicates that you get better performance out of it if you're nice because it imitates people, and I also like being nice. wearenotthesame.jpg

[urpartnerincrime@sh.itjust.works]

Currently

[earflap@reddthat.com]

That's the dumbest thing I've ever read holy shit

[usrtrv@sh.itjust.works]

Yea pretty much.