technology

23881 readers

294 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

1. Obviously abide by the sitewide code of conduct. Bigotry will be met with an immediate ban
2. This community is about technology. Offtopic is permitted as long as it is kept in the comment sections
3. Although this is not /c/libre, FOSS related posting is tolerated, and even welcome in the case of effort posts
4. We believe technology should be liberating. As such, avoid promoting proprietary and/or bourgeois technology
5. Explanatory posts to correct the potential mistakes a comrade made in a post of their own are allowed, as long as they remain respectful
6. No crypto (Bitcoin, NFT, etc.) speculation, unless it is purely informative and not too cringe
7. Absolutely no tech bro shit. If you have a good opinion of Silicon Valley billionaires please manifest yourself so we can ban you.

founded 5 years ago

MODERATORS

submitted 2 weeks ago by yogthos@lemmygrad.ml to c/technology@hexbear.net

9 comments fedilink hide all child comments

Instead of just generating the next response, it simulates entire conversation trees to find paths that achieve long-term goals.

How it works:

Generates multiple response candidates at each conversation state
Simulates how conversations might unfold down each branch (using the LLM to predict user responses)
Scores each trajectory on metrics like empathy, goal achievement, coherence
Uses MCTS with UCB1 to efficiently explore the most promising paths
Selects the response that leads to the best expected outcome

Limitations:

Scoring is done by the same LLM that generates responses
Branch pruning is naive - just threshold-based instead of something smarter like progressive widening
Memory usage grows with tree size, there currently no node recycling

you are viewing a single comment's thread
view the rest of the comments

[–] Skye@hexbear.net 6 points 2 weeks ago (1 children)

overthinking how someone might react to what it could say in multiple branches with growing resource usage

This is it, if they can get it to reliably decide to just not say anything at all in the end then I have been fully replaced madeline-sadeline

[–] TraschcanOfIdeology@hexbear.net 5 points 2 weeks ago

Lol same, what I was thinking while reading the features was "wow, they found a way to simulate masking!"