undefined | Better HN

0 pointsKoolKat238mo ago0 comments

I'd say we're not far off.

Looking at the human side, it takes a while to actually learn something. If you've recently read something it remains in your "context window". You need to dream about it, to think about, to revisit and repeat until you actually learn it and "update your internal model". We need a mechanism for continuous weight updating.

Goal-generation is pretty much covered by your body constantly drip-feeding your brain various hormones "ongoing input prompts".

0 comments

onemoresoop8mo ago

> I'd say we're not far off.

How are we not far off? How can LLMs generate goals and based on what?

FeepingCreature8mo ago

You just train it on the goal. Then it has that goal.

Alternately, you can train it on following a goal and then you have a system where you can specify a goal.

At sufficient scale, a model will already contain goal-following algorithms because those help predict the next token when the model is basetrained on goal-following entities, ie. humans. Goal-driven RL then brings those algorithms to prominence.

kordlessagain8mo ago

Random goal use is showing to be more important than training. Although, last year someone trained on the fly during the competition, which is pretty awesome when you think about it.

kelseyfrog8mo ago

How do you figure goal generation and supervised goal training are interchangeable?

2 more replies

NetRunnerSu8mo ago

Minimize prediction errors.

tsurba8mo ago

But are we close to doing that in real-time on any reasonably large model? I don’t think so.

1 more reply

NetRunnerSu8mo ago

Yes, you're right, that's what we're doing.

https://github.com/dmf-archive/PILF

KoolKat23OP8mo ago

Very interesting, thanks for the link.

j / k navigate · click thread line to collapse

0 pointsKoolKat238mo ago0 comments

I'd say we're not far off.

Goal-generation is pretty much covered by your body constantly drip-feeding your brain various hormones "ongoing input prompts".

0 comments

onemoresoop8mo ago

> I'd say we're not far off.

How are we not far off? How can LLMs generate goals and based on what?

FeepingCreature8mo ago

You just train it on the goal. Then it has that goal.

Alternately, you can train it on following a goal and then you have a system where you can specify a goal.

kordlessagain8mo ago

Random goal use is showing to be more important than training. Although, last year someone trained on the fly during the competition, which is pretty awesome when you think about it.

kelseyfrog8mo ago

How do you figure goal generation and supervised goal training are interchangeable?

2 more replies

NetRunnerSu8mo ago

Minimize prediction errors.

tsurba8mo ago

But are we close to doing that in real-time on any reasonably large model? I don’t think so.

1 more reply

NetRunnerSu8mo ago

Yes, you're right, that's what we're doing.

https://github.com/dmf-archive/PILF

KoolKat23OP8mo ago

Very interesting, thanks for the link.

j / k navigate · click thread line to collapse