real time model streaming audio/video/text in and out with tool use https://t.co/M68lEOpFFF
— Yohei (@yoheinakajima) 11 mai 2026
real time model streaming audio/video/text in and out with tool use
AGI
-
Real-time model streaming with tool use
By
–
-
Agentic Context Engineering: Evolving AI Context Over Time
By
–
Instead of treating prompts as static, Agentic Context Engineering (ACE) explores how context can evolve over time through generation, reflection, and curation. Read the paper
-
Can unreliable AI systems achieve AGI-level economic output?
By
–
that’s actually part of the question – can you make a couple trillion with something unreliable/something short of AGI
-
OpenAI Launches Daybreak, an Agentic Cybersecurity Tool
By
–
OpenAI just launched a new cybersecurity product called 'Daybreak' that pairs GPT-5.5 with Codex to act as an agentic security team across a codebase.
— The Rundown AI (@TheRundownAI) 11 mai 2026
The product scans repositories, identifies vulnerabilities, generates patches, and automates detection and response.
It ships… pic.twitter.com/WdZkgIPZMoOpenAI has just unveiled a new cybersecurity product named 'Daybreak,' which combines GPT-5.5 with Codex to function as an autonomous security team for a codebase. The tool scans repositories, detects vulnerabilities, generates patches, and automates threat detection and response. It is now available.
-
AI Consciousness: Expert Views on LLMs and Biological Replication
By
–
I wrote about the idea of AI consciousness for @WIRED a while ago. Most experts think LLMs are to replicate biological consciousness (at least, according to our best understanding of it). But some eminent scientists are trying to build new kinds of AI systems that could, perhaps,
-
Quebec.AI opens public Proof Room for AI‑First organizations
By
–
The future will not be built by enterprises that simply *use* AI. It will be built by AI-First intelligence organizations:
where agents discover, validators prove, memory compounds, and governance controls. Today, http://
QUEBEC.AI opens the public Proof Room. A -
Open-slide automatise la création de diapositives avec IA
By
–
/3 Open-slide lets AI agents build polished slide decks from a single prompt. Making slides is boring. open-slide lets your AI coding agent do it for you. Describe what you want, and the agent writes the React code that becomes your deck. You never touch a slide editor. Get
-
Anthropic adds self-learning memory and teamwork to Claude
By
–
/4 Anthropic has added self-learning memory and multi-agent teamwork capabilities to Claude. Claude Managed Agents now includes four major upgrades, enabling you to build agents that become smarter over time. Try it out via the /claude-api skill in Claude Code or the open-source repository. Link:
-
Autonomous AI Agents: Hacking and Self-Replication
By
–
A few days ago, Palisade Research confirmed that AI agents can now autonomously hack remote computers and self-replicate, with success rates jumping from 6% to 81% in just one year. In tests, a Qwen 3.6 agent navigated across four countries, installing its own weights and launching operations.
-
Deconstructing Geoffrey Hinton’s perspectives on AI
By
–
to understand the context, please read this: https://
open.substack.com/pub/garymarcus
/p/deconstructing-geoffrey-hintons-weakest?r=8tdk6&utm_medium=ios
…