The system that makes that possible within thirty minutes cost, let me be handwavy here, a billion dollars. But after you have it, you are much less reticent about cards with $100k limits running around. Because they don’t really have that limit except when you want them to.
SYSTEMS
-
JPMorgan’s Multi-Agent AI System for Investment Research
By
–
Learn how @jpmorgan developed a multi-agent system architecture for investment research.
— LangChain (@LangChain) 29 mai 2025
David Odomirok and Zheng Xue reveal how they built "Ask David" – a sophisticated multi-agent AI system designed to automate investment research for thousands of financial products.
Watch… pic.twitter.com/ljiMZAnPQILearn how @jpmorgan developed a multi-agent system architecture for investment research. David Odomirok and Zheng Xue reveal how they built "Ask David" – a sophisticated multi-agent AI system designed to automate investment research for thousands of financial products. Watch
-
AgentDNS: Root Domain Naming System for LLM Agents
By
–
AgentDNS: A Root Domain Naming System for LLM Agents
Paper: https://
arxiv.org/pdf/2505.22368
.pdf
…
Code: https://
github.com/agentdns (coming soon?) -
Computational Irreducibility and Openness in Pattern Recognition
By
–
You are right! But if I understand correctly, the property of openness itself amounts to the possibility of encountering new objects (= configurations of patterns), and computational irreducibility prevents predicting which patterns we will encounter?
-
Open vs Closed Systems: Predictability and Observer Influence
By
–
My point is that open systems are indistinguishable from closed systems in which the influence of the starting state on the observer cannot be predicted in advance
-
AI Agent Suna by @kortix bypasses anti-scraping measures for big websites like Zillow.
By
–
Finally found an AI Agent that is an absolute web scraping machine. Suna by @kortix basically built an agent that can bypass anti-scraping measures from big websites. It's pretty well know that Zillow has extremely robust anti-scraping barriers due to the vast repository of
-
Openness and Computational Irreducibility: Epistemic Equivalence
By
–
Openness seems epistemically indistinguishable from computational irreducibility?
-
Mathematical Models of Consciousness Community Launches Initiative
By
–
Yes! The Mathematical Models of Consciousness community (created by @JohannesKleiner
) is the place to be! -
Defining Purely Algorithmic Systems: Penrose and Computational Theory
By
–
How do you define a 'purely algorithmic system'? In the sense that Penrose uses it, it's equivalent to computational (constructive math, operations on representations via successive state transitions)
-
Google secretly used an AI to optimize itself internally
By
–
Google a gardé ça secret pendant des mois.
— VISION IA (@vision_ia) 27 mai 2025
Une IA en interne – nom de code Alpha Evolve – a optimisé ses puces, restructuré ses serveurs et influencé ses décisions stratégiques.
Pas une démo. Une IA déjà déployée, déjà active.
L'IA qui s’auto-améliorent.
Vous réalisez ce que… pic.twitter.com/mIzFHU0pZRGoogle kept this secret for months. An internal AI – codenamed Alpha Evolve – optimized its chips, restructured its servers, and influenced its strategic decisions. Not a demo. An AI already deployed, already active.
The self-improving AI. Do you realize what