[#Article] Gemini 2.0 Flash, the model paving the way for Google's AI agents https://actuia.com/actualite/gemini-2-0-flash-le-modele-qui-ouvre-la-voie-aux-agents-dia-de-google/
…
#AI #artificialintelligence
AGENTS
-
Gemini 2.0 Flash: Google’s New AI Agent Model
By
–
-
Meta FAIR Releases Nine Open Source AI Research Artifacts
By
–
Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from @jpineau1
. All of this -
Defining AI Agents: A User-Centric Framework for Lutra AI
By
–
I've been thinking about how to define AI Agents as well esp. as we're working through making them really usable at @Lutra_AI . What do you think of this user-centric way to frame it?
-
Data-Driven Market Strategy with AI Agent Playbooks
By
–
Links to agentic playbooks at https://
blog.lutra.ai/empower-your-m
arket-strategy-with-data-driven-insights
… -
New AI Agents Suite for Business Research and Insights
By
–
We're excited to share a new suite of AI agents that perform business research! 🤖
— Jiquan Ngiam (@JiquanNgiam) 12 décembre 2024
One of the most popular uses on Lutra is to perform web research on a large database or spreadsheet of accounts, leads, or potential hires. Having deep insights about them enables you to better… pic.twitter.com/eT6sGHJadEWe're excited to share a new suite of AI agents that perform business research! One of the most popular uses on Lutra is to perform web research on a large database or spreadsheet of accounts, leads, or potential hires. Having deep insights about them enables you to better
-
Model Self-Improvement: Emergent Behavior in AI Systems
By
–
Check out this example which showcases one of the most exciting research directions: self-improvement.
— Oriol Vinyals (@OriolVinyalsML) 12 décembre 2024
In it, you see this behavior emerging (!) when the model realizes (with a "Oops!") that it did a mistake, and fixes it to create the cute image.
Wild times. https://t.co/bSwfUa7QCD pic.twitter.com/TasWGsgn5sCheck out this example which showcases one of the most exciting research directions: self-improvement. In it, you see this behavior emerging (!) when the model realizes (with a "Oops!") that it did a mistake, and fixes it to create the cute image. Wild times.
-
AI NPCs Gain Long-Term Memory and Personality Development
By
–
Our AI NPCs in the AI People game now have Long-Term Memory (LTM), allowing them to remember their conversations with you.
— Marek Rosa | European🇪🇺 | South African🇿🇦 (@marek_rosa) 12 décembre 2024
We will continue improving and expanding LTM to include features like personality development, spatial memory, skill learning, and many more.
LTM runs… https://t.co/r9cFdFKlVQOur AI NPCs in the AI People game now have Long-Term Memory (LTM), allowing them to remember their conversations with you. We will continue improving and expanding LTM to include features like personality development, spatial memory, skill learning, and many more. LTM runs
-
PokeCampanion Agent-Based Chatbot Debuts at NeurIPS
By
–
Gotta catch 'em all at @NeurIPSConf! 🦾
— SambaNova (@SambaNovaAI) 12 décembre 2024
Head over to booth 56 & get to know PokeCampanion, an agent-based #chatbot that embodies different #Pokemon trainer personalities, focusing on competitive Pokémon battles.
DevPost here ➡️ https://t.co/Np5NmANib4 pic.twitter.com/DHjgPDVjkLGotta catch 'em all at @NeurIPSConf
! Head over to booth 56 & get to know PokeCampanion, an agent-based #chatbot that embodies different #Pokemon trainer personalities, focusing on competitive Pokémon battles. DevPost here https://
bit.ly/4fcWuvF -
Copilot Vision: AI Assistant Seeing Your Whole World
By
–
"…the ambition here feels somewhat limitless. What if an AI assistant could see your whole world, know what was what, and help you navigate it? That’s the big idea behind Copilot Vision." Couldn't have said it better myself, @adamclarkestes
. -
Custom Memory Systems Superior to General Approaches
By
–
Completely agree with this Bearish on general memory systems, need to be pretty custom