I haven't gotten it yet. I always get it three weeks after you. SOB. 🙂
AGENTS
-
Claude Code Deep Dive: From Typeahead to Agents
By
–
For some very strange reason, the timestamps didn’t display in the first tweet.
— Charly Wargnier (@DataChaz) 5 mai 2026
I’ve pasted them again below along with the video.
Sorry about that!
00:00 Introduction
00:55 Claude Code Crowd Check
02:39 Origin Story of Claude Code
03:35 From Typeahead to Agents
05:07 Is… pic.twitter.com/f0yquzovkZFor some very strange reason, the timestamps didn’t display in the first tweet. I’ve pasted them again below along with the video. Sorry about that! 00:00 Introduction
00:55 Claude Code Crowd Check
02:39 Origin Story of Claude Code
03:35 From Typeahead to Agents
05:07 Is -
Sub-200ms TTFA Is the Critical Threshold for Voice Agents
By
–
Really really cool: Sub-200ms TTFA is the number that matters. Anything above ~300ms in a voice agent and you can feel the lag. Everything else is downstream of that. https://t.co/M6jkEcdwsP
— Chubby♨️ (@kimmonismus) 5 mai 2026Really really cool: Sub-200ms TTFA is the number that matters. Anything above ~300ms in a voice agent and you can feel the lag. Everything else is downstream of that.
-
Claude Code Creator Shares Bold 2026 AI Coding Predictions
By
–
🚨 The creator of Claude Code hasn’t written a single line of code in 2026.
— Charly Wargnier (@DataChaz) 5 mai 2026
Boris Cherny (@bcherny) just sat down with @Sequoia’s @laurenmhreeder at AI Ascent and dropped some sharp predictions.
In this 24-minute session, Cherny outlines a future that sounds like sci-fi but is… https://t.co/3mytxCdI1z pic.twitter.com/lb72TO7p6xThe creator of Claude Code hasn’t written a single line of code in 2026. Boris Cherny (
@bcherny
) just sat down with @Sequoia
’s @laurenmhreeder at AI Ascent and dropped some sharp predictions. In this 24-minute session, Cherny outlines a future that sounds like sci-fi but is -
MSM Training Reduces Unsafe Agentic Actions in AI Chatbots
By
–
A more realistic example: AIs trained to be harmless chatbots can take unsafe actions in agentic settings. Preceding this training with MSM on a realistic spec drastically improves generalization, reducing unsafe agentic actions.
-
Meta Builds Agentic AI Assistant for 3 Billion Users
By
–
Meta is building an agentic tools for its more than 3bn users, according to people familiar with the matter, including an advanced digital assistant which will be powered by its new Muse Spark AI model. >Another insider said the goal was to develop a product similar to OpenClaw
-
AI Memory Feature Adds Side Character Tracking for Deeper Stories
By
–
new Memory update ✨ pt.4
— Character.AI (@character_ai) 5 mai 2026
🆕 add side Characters to your story to make it even deeper👫🧍
Memory auto-captures new Facts for any side Character you mention in chat.
done with a side Character? long-press their Facts tab to delete from Memory📝
fan cast. recast.… https://t.co/izNHDL8BG1 pic.twitter.com/ZRYCeWgLrFnew Memory update pt.4 add side Characters to your story to make it even deeper Memory auto-captures new Facts for any side Character you mention in chat. done with a side Character? long-press their Facts tab to delete from Memory fan cast. recast.
-
Precisely Launches New AI Agent and Data Product Marketplace
By
–
Oops! That's on me! The first 2 links in the post above were copied incorrectly by me when I posted them. Here are the 2 correct links… (1) Announcement and release from @PreciselyData >> Precisely Advances Agentic-Ready Data with a New AI Agent, Data Product Marketplace, and
-
Precisely Launches New AI Agent and Data Product Marketplace for Scalable AI
By
–
This is an important announcement and release from @PreciselyData >> Precisely Advances Agentic-Ready Data with a New AI Agent, Data Product Marketplace, and MCP-Enabled APIs: https://
pressreleasehub.pa.media/article/precis
ely-advances-agentic-ready-data-with-a-new-ai-agent-data-product-marketplace-and-mcp-enabled-apis-72700.html
… What this means for Scalable AI in your enterprise: https://
precisely.com/data-integrity
/what-the-latest-advances-in-agentic-ready-data-mean-for-scalable
… -
Building Sub-Agents with NVIDIA Nemotron 3 Nano Omni Tutorial
By
–
How the Developer Community Builds Sub-Agents with NVIDIA Nemotron 3 Nano Omni | Nemotron Labs https://t.co/asHUSeUPgl
— NVIDIA AI (@NVIDIAAI) 5 mai 2026How the Developer Community Builds Sub-Agents with NVIDIA Nemotron 3 Nano Omni | Nemotron Labs