I'm not sure they do, but Llama 3.1 doesn't for example so you're comparing apples and oranges anyway
AGI
-
Safe Superintelligence raises 1 billion for secure AI
By
–
Safe Superintelligence raises 1 billion dollars to accelerate the development of secure AI systems https://actuia.com/actualite/safe-superintelligence-leve-1-milliard-de-dollars-pour-accelerer-le-developpement-de-systemes-dia-securises/
… #AI #ArtificialIntelligence -
Reflection technique between AI models by Fernando Neto
By
–
Example from the great @FernandoNetoAi of reflection with another model.
-
Reflection CoT Evaluation Methods Comparability Issues
By
–
This is super cool but I have a lot of questions. First, reflection = CoT on steroids. It means you can't compare these scores at all. Remember when people made fun of Gemini for providing CoT results for MMLU? This is a lot worse. Secondly, if you don't parse the output and
-
Graph-Based Agent Evolution: Improving Self-Understanding Capabilities
By
–
it’s an evolution of the graph based agent i’ve been sharing earlier this year where the focus is on getting it to understand itself well
-
Rebuilding BabyAGI: New Approach After Months of Development
By
–
context for the curious… i started rebuilding babyagi earlier this year based on learning from the previous iterations but it slowly got a bit more complicated, and i’d been stuck for a few months (which I didn’t realize at the time but do now) the new approach is similar but
-
Developer breakthrough with new BabyAGI approach overnight
By
–
something clicked 2 nights ago so I was up 12-2 trying a new approach to babyagi. then again last night cuz i love where this is going. i need sleep but i kind of just want to power through on getting this idea down…
-
People seeking to fix everything: consequences and societal impact
By
–
True, but then the people who want to “fix” everything come looking for you.
-
Infinite Interactive Worlds: AI Training via Diffusion Models
By
–
> create interactive world
— Yohei (@yoheinakajima) 5 septembre 2024
> train ai to play
> record video of ai playing
> train diffusion model on frames/actions
> you now haz infinite interactive world https://t.co/bBBS38J0rf> create interactive world
> train ai to play
> record video of ai playing
> train diffusion model on frames/actions
> you now haz infinite interactive world