this post was submitted on 23 Nov 2023
1 points (100.0% liked)

Machine Learning

1 readers
1 users here now

Community Rules:

founded 1 year ago
MODERATORS
 

According to one of the sources, long-time executive Mira Murati told employees on Wednesday that a letter about the AI breakthrough called Q* (pronounced Q-Star), precipitated the board's actions.

The maker of ChatGPT had made progress on Q*, which some internally believe could be a breakthrough in the startup's search for superintelligence, also known as artificial general intelligence (AGI), one of the people told Reuters. OpenAI defines AGI as AI systems that are smarter than humans.

https://www.reuters.com/technology/sam-altmans-ouster-openai-was-precipitated-by-letter-board-about-ai-breakthrough-2023-11-22/

you are viewing a single comment's thread
view the rest of the comments
[–] residentmouse@alien.top 1 points 11 months ago (4 children)

OK, so full speculation: this project could be an impl. of Q-Learning (i.e unsupervised reinforcement learning) on an internal GPT model. This would no doubt be an agent model.

Other evidence? The * implies a graph traversal algorithm, which obviously plays a huge role in RL exploration, but also GPT models are already doing their own graph traversal via beam search to do next token prediction.

Are they perhaps hooking up an RL trained model to replace their beam search?

[–] VirtualHat@alien.top 1 points 11 months ago (1 children)

The star in Q* traditionally refers to a policy which is optimal.

[–] JustOneAvailableName@alien.top 1 points 11 months ago

Value function, pi is policy

[–] Material_Policy6327@alien.top 1 points 11 months ago

That’s my feeling on what’s actually being reported Poorly by the news

[–] tomvorlostriddle@alien.top 1 points 11 months ago

of Q-Learning (i.e unsupervised reinforcement learning) on an internal GPT model.

Potential efficacity aside, imagine the scenario of those blabbermouths just eternally yapping among each other and that unbelievably boring wall of text should be what brings about superintelligence :)

[–] ReptileCultist@alien.top 1 points 11 months ago

GPT models are already doing their own graph traversal via beam search to do next token prediction.

I don't think GPT is often used in conjunction with beam search or is it?