Roberto H Luna

@LyfsDiary @arafatkatze There is a better interface ;) github.com/Miosa-osa/Busi…

@arafatkatze I still don't understand how people are managing their cognitive load with all the moving parts.

Calling it now, This form factor of multi agent orchestration will overtake every other agentic UX in the next six months. Doesn’t matter if it’s coding agent, product management agent or something else. Every multi agent flow of frontier models currently suffers from 2 main problems 1. Inference bound: Most of the time you are just waiting on inference while the agent rips on code in the background and that can take 8-10 minutes fairly regularly so the wait time very expensive productivity wise. 2. Take Isolation: you will work on the same mutating “source code ” with multiple agents in parallel each of which are inference bound and so eventually you will run into countless merge conflicts The kanban board solves for both of them by giving you the ability to act as an engineer manager for your IC individual agents, watching them cleanly with a clear headline level out look of every parallel agent. It works seamlessly with any coding agent whether it’s cline or codex or Claude code. To me this is a mental model shift that takes 10 minutes, you use the same coding agents like you always used before this but it will fundamentally morph your coding agent experience. Try out kanban and let us know what you think. npm i -g cline Is all you need.

@dylanworr usefastlane.ai

casually building the new tiktok of ai era

@dylanworr github.com/robertohluna/L…

Tryna find a guy whos good at pre training llms is like getting to thefinal trainer level in Pokémon

@kimmonismus These two fellas wanna dance

OpenAI is backing Isara, a new startup founded by two 23-year-old AI researchers that coordinates thousands of AI agents to solve complex problems, like using ~2,000 agents to forecast gold prices. The company just raised $94M at a $650M valuation and plans to sell predictive modeling tools to finance firms first.

@ROMEO_77R @WSJ Yup

@WSJ So now the bots aren’t just working… they’re networking too 🤖 At this point, humans are just middle management in their own economy.

Exclusive: OpenAI is backing a new AI startup that aims to build software allowing so-called AI “agents” to communicate and solve complex problems in industries such as finance and biotech on.wsj.com/4bTvwKd

@danielperk64718 Nah this shits noise. If they were applying a proper organizational structure I’d be applauding but they are not, and they are following last years standard of agent teams, with a CEO and all that shit

Paperclip got the crazy tech 💦💦💦💦

@cryptic_mazey Nah this shit doesn’t even properly use organization theory, it’s like the kid version of a company, just call it agent teams at this point

He might actually be the goat…

@hark_labs What the fuck kind of noise is this???

Introducing Hark, an AI lab building the most advanced, personal intelligence in the world. We're creating intelligent foundation models paired with next generation hardware designed to serve as a universal interface between humans and machines. hark.com

@CeciStalls 🧢

We're building the world's safest vibe coding platform.

@mil0theminer LOL

“Introducing [crappy name] The worlds FIRST agentic app builder”

@adisingh orgo.ai how is this different than this

Software for agents isn’t enough. We need computers for agents

@4shadowed @somewheresy Looks like a classic case of semantics to me. Call it what you want, Scam Altman posting about Peter joining OpenAI is all I need to know, to know it’s compromised

@robertohluna @somewheresy No it’s not. It’s owned by the OpenClaw Foundation, OpenAI is just one of our several sponsors

hermes agent will eat openclaw because openclaw is terrible at community management

@tomosman Yes there is no choice

Everyone is building the same thing.

@codyschneiderxx Done

I want you to build software I can operate with Claude Code everything everything can be operated with an agent

@advaitpaliwal orgo.ai @nickvasiles

Introducing Agent Computer Cloud computers for AI agents in <0.5s with persistent disk, shared credentials, and SSH access agentcomputer.ai

@jasonkneen @yiliush I find all your work quite interesting, you seem to have good ideas

@yiliush My own approach

source code now available github.com/collaborator-a…

@jennyzhangzt All this noise, yet still you haven’t figured out how to optimally encode the intent to the agents to have them know how and why to improve themselves

Introducing Hyperagents: an AI system that not only improves at solving tasks, but also improves how it improves itself. The Darwin Gödel Machine (DGM) demonstrated that open-ended self-improvement is possible by iteratively generating and evaluating improved agents, yet it relies on a key assumption: that improvements in task performance (e.g., coding ability) translate into improvements in the self-improvement process itself. This alignment holds in coding, where both evaluation and modification are expressed in the same domain, but breaks down more generally. As a result, prior systems remain constrained by fixed, handcrafted meta-level procedures that do not themselves evolve. We introduce Hyperagents – self-referential agents that can modify both their task-solving behavior and the process that generates future improvements. This enables what we call metacognitive self-modification: learning not just to perform better, but to improve at improving. We instantiate this framework as DGM-Hyperagents (DGM-H), an extension of the DGM in which both task-solving behavior and the self-improvement procedure are editable and subject to evolution. Across diverse domains (coding, paper review, robotics reward design, and Olympiad-level math solution grading), hyperagents enable continuous performance improvements over time and outperform baselines without self-improvement or open-ended exploration, as well as prior self-improving systems (including DGM). DGM-H also improves the process by which new agents are generated (e.g. persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. This work was done during my internship at Meta (@AIatMeta), in collaboration with Bingchen Zhao (@BingchenZhao), Wannan Yang (@winnieyangwn), Jakob Foerster (@j_foerst), Jeff Clune (@jeffclune), Minqi Jiang (@MinqiJiang), Sam Devlin (@smdvln), and Tatiana Shavrina (@rybolos).

Shocker

@Teknium @openclaw OpenAI and Claude are going to completely reverse engineer and steal everyone’s shit,

@openclaw cloning from us*

OpenClaw 2026.3.22 🦞 🏪 ClawHub plugin marketplace 🤖 MiniMax M2.7, GPT-5.4-mini/nano + per-agent reasoning 💬 /btw side questions 🏖️ OpenShell + SSH sandboxes 🌐 Exa, Tavily, Firecrawl search This release is so big it needs its own table of contents. github.com/openclaw/openc…