By
–
Time to fire your agent 🤖 👋
— Pika (@pika_labs) 31 mars 2026
Pika AI Selves have all the agentic connections and skills, plus actual personalities. Have them put your taste to work with Pika Powers. pic.twitter.com/eT0QHXTeO3
Time to fire your agent Pika AI Selves have all the agentic connections and skills, plus actual personalities. Have them put your taste to work with Pika Powers.
By
–
Try it out at Pika dot me or our new iphone app https://
apps.apple.com/us/app/pika-ai
-self-agent/id6758411447
…
By
–
Today, we release LFM2.5-350M. Agentic loops at 350M parameters. A 350M model trained for reliable data extraction and tool use, where models at this scale typically struggle. <500MB when quantized, built for environments where compute, memory, and latency are constrained. 🧵
→ View original post on X — @thom_wolf, 2026-03-31 17:17 UTC
By
–
The first paper from the Secure Intelligence Institute responds to NIST's request for information on securing autonomous agents. Read the paper on arXiv: arxiv.org/abs/2603.12230 [Translated from EN to English]
→ View original post on X — @perplexity_ai, 2026-03-31 17:16 UTC
By
–
New conceptual guide: The agent improvement loop starts with a trace Tracing is the foundational primitive for improving agents. A trace gives you the full behavioral record of what an agent actually did. From there, teams can enrich traces with evals and human feedback,
By
–
Have an idea? Make it a production agent ready in 5 minutes through @DataRobot
By
–
🦞 TL;DR: New Job at Microsoft. Bringing OpenClaw + personal agents to Microsoft 365! My goal is to help usher in a new generation of workplace proactive assistants, ones that lighten your load by taking on tasks end-to-end, and that can also step in proactively when they can help. As part of this mission, I’ll be partnering with the @OpenClaw + M365 community to bring the energy of this work to our customers. We’ve already hit the ground running with a fully integrated Teams plugin for OpenClaw, and I can’t wait to help usher in the era of personal agents at work.
→ View original post on X — @paulroetzer, 2026-03-31 16:52 UTC
By
–
Nature research paper: Towards end-to-end automation of AI research
go.nature.com/4rSOGFK [Translated from EN to English]
→ View original post on X — @sakanaailabs, 2026-03-31 16:52 UTC
By
–
New LangChain Academy Course Launch: Monitoring Production Agents
— LangChain (@LangChain) 31 mars 2026
Shipping agents to production is hard. Unlike traditional software, agents are non-deterministic. Users can say anything, and the same input can produce different outputs.
You can’t rely on pre-launch testing… pic.twitter.com/rbj9Ror8Og
New LangChain Academy Course Launch: Monitoring Production Agents Shipping agents to production is hard. Unlike traditional software, agents are non-deterministic. Users can say anything, and the same input can produce different outputs. You can’t rely on pre-launch testing
By
–
I’ve spent at least 100 hours setting up, training, and working with @openclaw Read the docs. Peeked into the source code. Edited config files by hand. Walked friends though their setup. Then, I wrote down everything I know. Here it is: The Ultimate 0 > 🦞 Guide ty ty to @lennysan @nateliason @davemorin @steipete @lindsmccallum @elawless for early feedback. gl hf snap snap 🦞lennysnewsletter.com/p/openc… Lenny Rachitsky (@lennysan) OpenClaw: The complete guide @ClaireVo has just put together the definitive guide to getting started with and mastering OpenClaw. Building on our podcast episode, this post covers everything you need to know, from first install to multi-agent setups, plus the real costs and security gotchas most people skip over. Whether you’re brand new to OpenClaw or already running one, Claire’s guide will level you up. Find it here 🦞: lennysnewsletter.com/p/openc… — https://nitter.net/lennysan/status/2039002789666562165#m
→ View original post on X — @paulroetzer, 2026-03-31 16:06 UTC