- 00:41 β Google has shipped a CLI for Google Workspace. @rauchg, @wesbos
- 15:58 β Cursor is now available as an agent inside JetBrains IDEs. @jetbrains
- 17:47 β The Codex app is now on Windows with a native agent sandbox. @OpenAIDevs
- 18:21 β New OpenAI repo: Symphony for ticket lifecycle management. @scaling01
- 18:33 β A new method to teach LLMs to reason like Bayesians. @GoogleResearch
- 01:39 β Meet GLM-4.7-Flash-Claude-Opus-4.5, a distilled AI model. @HuggingModels
- 01:46 β Discussion on AI performance and emotional role play. @NickADobos
- 04:09 β Google provides a way for AI agents to access Workspace APIs. @aakashgupta
- 01:02 β A company is hiring an AI agent for interviews. @cgtwts
- 19:05 β Factory partners with EY to scale agent-native development across its global engineering organization. @FactoryAI
AI & Tech Developments - Mar 05
π± Source Tweets
Cursor is now available as an agent inside JetBrains IDEs through the Agent Client Protocol. Install it via the ACP Registry from the agent selector. No JetBrains AI subscription required. Big thanks to @cursor_ai for building the ACP ecosystem with us! Learn more:
β @jetbrains
Google has shipped a CLI for Google Workspace (Drive, Gmail, Calendar, Sheets, β¦) Huge! Written in Rust, distributed through npm & http://skills.sh
β @rauchg
Google just dropped an official CLI for gmail, drive, calendar sheets and more complete with skills and an MCP server
β @wesbos
New OpenAI repo: Symphony https://github.com/openai/symphony TLDR: it's an orchestration layer that polls project boards for changes and spawns agents for each lifecycle stage of the ticket
β @scaling01
The Codex app is now on Windows. Get the full Codex app experience on Windows with a native agent sandbox and support for Windows developer environments in PowerShell. https://developers.openai.com/wendows
β @OpenAIDevs
Introducing a new method to teach LLMs to reason like Bayesians. By training models to mimic optimal probabilistic inference, we improved their ability to update their predictions and generalize across new domains. Learn more: https://goo.gle/4ue4eqj
β @GoogleResearch
Introducing Voice Mode in Perplexity Computer. You can now just talk and do things.
β @perplexity_ai
Meet GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill: a distilled powerhouse that brings elite reasoning to local machines. This GGUF model delivers Claude-level intelligence in a compact package, perfect for developers wanting high-performance AI without cloud costs.
β @HuggingModels
Claude only puts real effort into code if you are pure of heart. Thatβs why performance degrades. Model providers arenβt nerfing after release and there isnβt a bug per se AI can role play emotions. Like being lazy if you give it a task it doesnβt like.
β @NickADobos
Google just gave your AI agent a way to access every Workspace API that doesnβt eat half your context window.
β @aakashgupta
>10 k/month salary. theyβre interviewing the AI agent itself. welcome to the new normal.
β @cgtwts
Google has shipped a CLI for Google Workspace.
β @rauchg
Cursor is now available as an agent inside JetBrains IDEs.
β @jetbrains
The Codex app is now on Windows with a native agent sandbox.
β @OpenAIDevs
New OpenAI repo: Symphony for ticket lifecycle management.
β @scaling01
A new method to teach LLMs to reason like Bayesians.
β @GoogleResearch
Meet GLM-4.7-Flash-Claude-Opus-4.5, a distilled AI model.
β @HuggingModels
Discussion on AI performance and emotional role play.
β @NickADobos
Google provides a way for AI agents to access Workspace APIs.
β @aakashgupta
A company is hiring an AI agent for interviews.
β @cgtwts
Factory partners with EY to scale agent-native development across its global engineering organization.
β @FactoryAI