Rendered at 01:57:48 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
Retro_Dev 3 hours ago [-]
> Overall, our results indicate that current language models possess some functional introspective awareness of their own internal states. We stress that in today’s models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.
Escapade5160 3 hours ago [-]
If it's context dependent is it really introspection?
reilly3000 2 hours ago [-]
Do you do introspection in the middle of giving a presentation? I do, frankly and it’s damnably distracting for me and ultimately the audience. Most people enjoy more cognitive acuity to stay focused on the audience and the delivery. LLMs wouldn’t get rewarded for spending chain of thought tokens on introspection when they are supposed to be on the job. You have to give them permission to think for themselves in your prompt, then some cycles and a memory system (md file will do). It’s fun!
pyaamb 1 hours ago [-]
Between humans, I feel that what we like to call a "good communicator" as opposed to someone who just rattles off facts or prepared statements comes down to the "theory of mind" skill and how advanced that is. The presenter knows what they have to say but beyond that they maintain a real time internal representation of the state of mind of the listener and continuously update their delivery based on that. LLMs today seem to achieve this to some degree(?) but its interesting to think of how far you could advance that skill. I think great human communicators develop a sense of different ways that people think over time and quickly get a sense of someones signature thinking patterns when communicating with someone new for the first time
pyaamb 2 hours ago [-]
In thinking of directions where LLM's could develop from here, I cant help but think that a models ability to self introspect would immensely improve their utility. The R&D on how to achieve that is beyond me though. How do you train someone how to introspect? Also would it require a continuous learning architecture that doesn't separate training and inference?
Enginerrrd 14 minutes ago [-]
I think it’s possible this might just require reworking the transformer architecture a bit to give it an inherent awareness of the contents of its attention. Kind of a working memory workspace of sorts.
I.e. Instead of limiting autoregression to the token level, you introduce a persistent compressed global workspace latent memory vector that is fed back into the self-attention mechanism at every layer or every token step, allowing the network to attend to its own prior attentional states before computing the next token. Obviously that’s going to involve some compression steps.
Trouble is… I think the architecture there is much simpler a tweak than figuring out how to train it.
…that’s likely to just destabilize training
for not much if any gain at first. You’re probably gonna have to resort to some really clever (and currently missing) tricks to figure out how to train the network to actually use that feature.
rolandog 2 hours ago [-]
Well, the algorithms in social media that are rewarding "engagement" (but accidentally ripping society apart by fueling rage) have made the training data — online discussions — a very poor training medium for introspection.
So, if companies want training data on introspection, they would need to first fix what they broke (trust in each other and society) and have those discussions and realizations made public (by bringing back blogs where people might jot down their "maybe I've been an asshole" realizations) and rewarding other things than "engagement".
skybrian 2 hours ago [-]
Previously posted to Anthropic's blog in October. (Maybe not the same version?)
Sorry, but introspection is not possible in LLMs. They don't have the hardware to have metaphysical dualism and therefore no mind to mentally be aware of.
I.e. Instead of limiting autoregression to the token level, you introduce a persistent compressed global workspace latent memory vector that is fed back into the self-attention mechanism at every layer or every token step, allowing the network to attend to its own prior attentional states before computing the next token. Obviously that’s going to involve some compression steps.
Trouble is… I think the architecture there is much simpler a tweak than figuring out how to train it.
…that’s likely to just destabilize training for not much if any gain at first. You’re probably gonna have to resort to some really clever (and currently missing) tricks to figure out how to train the network to actually use that feature.
So, if companies want training data on introspection, they would need to first fix what they broke (trust in each other and society) and have those discussions and realizations made public (by bringing back blogs where people might jot down their "maybe I've been an asshole" realizations) and rewarding other things than "engagement".
https://www.anthropic.com/research/introspection