[awesome_dude]

Like I said, the AI does exactly what I intend for it to do.

Almost, as I said earler, like the AI has processed my request, realised that I am referring to the context of the earlier discussions, and moved on to the next prompt exactly how I have expected it to

Given the two very VERY dumb responses, and multiple people down voting, I am reminded how thankful I am that AI is around now, because it understood what you clearly don't.

I didn't expect it to delete the internet, the world, the universe, or anything, it didn't read my request as an instruction to do so... yet you and that other imbecile seem to think that that's what was meant... even after me saying it was doing as I wanted.

/me shrugs - now fight me how your interpretation is the only right one... go on... (like you and that other person already are)

One thing I am not going to miss is the toxic "We know better" responses from JUNIORS

[baq]

I think you completely misunderstood me, actually. I explicitly say if it works, great, no sarcasm. LLMs are finicky beasts. Just keep in mind they don’t really forget anything, if you tell it to forget, the things you told it before are still taken into the matrix multiplication mincers and influence outputs just the same. Any forgetting is pretend in that your ‘please forget’ is mixed in after.

But back to scheduled programming: if it works, great. This is prompt engineering, not magic, not humans, just tools. It pays to know how they work, though.

[lsaferite]

It's beyond possible that the LLM Chat Agent has tools to self manage context. I've written tools that let an agent compress chunks of context, search those chunks, and uncompress them at will. It'd be trivial to add a tool that allowed the agent to ignore that tool call and anything before it.

[famouswaffles]

>the things you told it before are still taken into the matrix multiplication mincers and influence outputs just the same.

Not the same no. Models chooses how much attention to give each token based on all current context. Probably that phrase, or something like it, makes the model give much less attention to those tokens than it would without it.

[awesome_dude]

No.

I think that you are misunderstanding EVERYTHING

Answer this:

1. Why would I care what the other interpretation of the wording I GAVE is?

2. What would that interpretation matter when the LLM/AI took my exact meaning and behaved correctly?

Finally - you think you "know how it works"????

Because you tried to correct me with an incorrect interpretation?

F0ff

[baq]

Well ask it to tell you what it forgot. Over and out.

[dns_snek]

> I am reminded how thankful I am that AI is around now, because it understood what you clearly don't.

We understand what you're saying just fine but what you're saying is simply wrong as a matter of technical fact. All of that context still exists and still degrades the output even if the model has fooled you into thinking that it doesn't. Therefore recommending it as an alternative to actually clearing the context is bad advice.

It's similar to how a model can be given a secret password and instructed not to reveal it to anyone under any circumstances. It's going to reject naive attempts at first, but it's always going to reveal it eventually.

[awesome_dude]

What I'm saying is.. I tell the AI to "forget everything" and it understands what I mean... and you're arguing that it cannot do... what you INCORRECTLY think is being said

I get that you're not very intelligent, but do you have to show it repeatedly?

[dns_snek]

Again, we understand your argument and I don't doubt that the model "understands" your request and agrees to do it (insofar that LLMs are able to "understand" anything).

But just because the model is agreeing to "forget everything" doesn't mean that it's actually clearing its own context, and because it's not actually clearing its own context it means that all the output quality problems associated with an overfilled context continue to apply, even if the model is convincingly pretending to have forgotten everything. Therefore your original interjection of "instead of clearing the context you can just ask it to forget" was mistaken and misleading.

These conversations would be way easier if you didn't go around labeling everyone an idiot, believing that we're all incapable of understanding your rather trivial point while ignoring everything we say. In an alternative universe this could've been:

> You can ask it to forget.

> Models don't work like that.

> Oh, I didn't know that, thanks!

[famouswaffles]

Just because it's not mechanically actually forgetting everything doesn't mean the phrase isn't having a non trivial effect (that isn't 'pretend'). Mechanically, based on all current context, Transformers choose how much attention/weight to give to each preceding token. Very likely, the phrase makes the model pay much less attention to those tokens, alleviating the issues of context rot in most (or a non negligible amount of) scenarios.

[lsaferite]

You should probably stop resorting to personal attacks as it's against hn rules.