I think I saw @pirroh mentioned they started rolling out 4 in their agent, so I think maybe I got help from it
AGENTS
-
OpenAI Updates Operator ChatGPT with Latest o3 Reasoning Model
By
–
Operator OpenAI o3 Operator in ChatGPT has been updated with our latest reasoning model. https://
operator.chatgpt.com -
Building AI App with Replit Agent and Codex Integration
By
–
vibe coded with @replit agent, using 142 check points ($35.50) so far plus some assistance from Codex which you can see in the PRs here's the github:
-
AIs Running Company: Insights Into Future Business Operations
By
–
They Let AIs Run a Company: What Unfolded Speaks Volumes About the Future We’re Heading Toward https://
search.app/HQLXL #FutureIsNow #FutureTech #Tech #AI #business #company #executive #csuite #ArtificialIntelligence @lexfridman @KirkDBorne @Ronald_vanLoon @erikbryn -
Alpha-Factory v1: Meta-Agentic AGI Agent Framework Launch
By
–
[ Alpha‑Factory v1 — META-AGENTIC α‑AGI ] Mission End‑to‑end : Identify → Out‑Learn → Out‑Think → Out‑Design → Out‑Strategise → Out‑Execute GitHub : https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0
… #AGIALPHA #AlphaInsight #MetaAgentic -
Alpha-Factory v1: Meta-Agentic AGI Framework Released
By
–
[ Alpha‑Factory v1 — META-AGENTIC α‑AGI ] Mission End‑to‑end: Identify → Out‑Learn → Out‑Think → Out‑Design → Out‑Strategise → Out‑Execute GitHub: https://
github.com/MontrealAI/AGI
-Alpha-Agent-v0
… #AGIALPHA #AlphaInsight #MetaAgentic -
Request for Background Agents System Prompts
By
–
@elder_plinius do you have the system prompts for background agents?
-
Gemini App Evolution: Universal Assistant Vision Unveiled
By
–
Our vision for a universal assistant, the next evolution of the Gemini app…
-
API upgrades enable agentic apps with live code and file processing
By
–
5. Brand-new API upgrades: Run code live Connect with Model Context Protocol Upload and process files Cache prompts for faster, cheaper responses Build agentic apps without friction.
-
Claude Opus 4 tops benchmarks, built for long multi-step workflows
By
–
1. Claude Opus 4 Tops SWE-bench (72.5%) and Terminal-bench (43.2%) Capable of hours-long, multi-step workflows Used by leaders like Cursor, Replit, Block & Rakuten Trusted for complex refactoring, debugging & agentic workflows