ça aurait dû être deployé J-0 au lancement de copilot https://t.co/VP2CgDu2Kc
— ⚡Jessy SEO formation #IA générative #chatGPT 🦊 (@jessyseonoob) 28 avril 2026
It should have been deployed D-1 at the launch of Copilot.
TOOLS
-
Copilot Feature Deployment Timing Criticized by User
By
–
-
BigLaw Bench: Evaluating AI Legal Research Capabilities
By
–
We recently partnered with @harvey on BigLaw Bench: Research, evaluating how well models handle real end-to-end case law research, identifying the right authorities, applying legal reasoning, and delivering answers you can actually use. It also shows where things still break and
-
Skill Retrieval Augmentation for Agentic AI Systems
By
–
// Skill Retrieval Augmentation for Agentic AI // Great read for AI devs. (bookmark it) It's on finding efficient ways to incorporate skills for agents. The work introduces Skill Retrieval Augmentation (SRA) and SRA-Bench: 26,262 skills, 636 gold skills, 5,400
-
AI Models Commoditize While Integration Layers Fragment Next Two Years
By
–
Models will keep commoditizing while platform/execution layers fragment, the next 2 years are mostly an integration layer fight.
-
ABB’s AI Copilot Resolves 80% Faults via QR Documentation
By
–
David Lincoln at ABB walked me through how they spent three years tuning their AI copilot on Microsoft AI Foundry to answer only from ABB's own device documentation. No guesses. No hallucination risk. That is why 80% of faults get resolved from a QR scan. #abb_ai pic.twitter.com/NmYMbUFC4n
— Lucian Fogoros (@fogoros) 28 avril 2026David Lincoln at ABB walked me through how they spent three years tuning their AI copilot on Microsoft AI Foundry to answer only from ABB's own device documentation. No guesses. No hallucination risk. That is why 80% of faults get resolved from a QR scan. #abb_ai
-
ListenLabs Agents Analyze Conversations Building Custom Data Tables
By
–
At @ListenLabs, agents analyze data from conversations by building their own tables — adding columns like "user sentiment," filling in values automatically, then charting the results.
— LangChain (@LangChain) 28 avril 2026
Co-Founder & CTO @florian_jue runs through how this works on the Max Agency podcast hosted by… pic.twitter.com/XcrHSg4QbvAt @ListenLabs
, agents analyze data from conversations by building their own tables — adding columns like "user sentiment," filling in values automatically, then charting the results. Co-Founder & CTO @florian_jue runs through how this works on the Max Agency podcast hosted by -
Typeless: AI Writing Tool Closes Brain-to-Keyboard Speed Gap
By
–
Your brain runs at 400 words per minute,Your fingers type 40. That gap is why you stare at the doc for an hour and write it in ten. Typeless closes the gap. You speak, it lands as polished writing. Students get 50% off with a school email.
-
Brother builds Hono UI framework for web development
By
–
but it should be my brother built it as i was generated ui with hono he just thought it was a good name for it, he'd change it to stop confusion for sure (oh and its live! https://
honoui.com) -
Codex Automates Developer Workflows and Pull Request Management
By
–
For developers, Codex can keep PR work moving: investigate feedback, make edits, run checks, and babysit CI until the work is actually ready pic.twitter.com/yu22YhPczI
— Vaibhav (VB) Srivastav (@reach_vb) 28 avril 2026For developers, Codex can keep PR work moving: investigate feedback, make edits, run checks, and babysit CI until the work is actually ready
-
Codex Now Produces and Revises Spreadsheets, Docs, Slides
By
–
Artifacts are now first-class
— Vaibhav (VB) Srivastav (@reach_vb) 28 avril 2026
Codex can produce and revise spreadsheets, docs, slides, and other files, with previews that make the output easier to inspect before you ship it pic.twitter.com/30PYT2WohiArtifacts are now first-class Codex can produce and revise spreadsheets, docs, slides, and other files, with previews that make the output easier to inspect before you ship it