This is a nice paper, well executed! @scott_e_reed had this in mind when developing Gato https://
arxiv.org/abs/2205.06175 — I’m glad to see the idea executed with a humanoid and I’d love to see more work along this direction. Gato stood for General AgenT One. Sadly, we weren’t able to
AGENTS
-
Paper praised for executing Gato idea with humanoid; more work desired
By
–
-
Skild Brain AI enables robots to handle unfamiliar environments
By
–
Skild Brain is an AI system developed by Skild AI that helps robots operate in unfamiliar environments.
— Amitav Bhattacharjee (@bamitav) 27 juin 2026
It enables different types of robots to complete real-world tasks without prior training or hard-coded instructions.
By controlling robot movements in real time, it makes… pic.twitter.com/PGsCgd9mYHSkild Brain is an AI system developed by Skild AI that helps robots operate in unfamiliar environments. It enables different types of robots to complete real-world tasks without prior training or hard-coded instructions. By controlling robot movements in real time, it makes
-
Using video to learn control representations, touch important
By
–
I think they also emerge from video. This is what I was the most excited about when helping with projects like Veo. My intent was never to create slop videos, but rather to use video to learn representations for control. I must say however that touch is super important and highly
-
BrowserBC explores efficient web agents by distilling human flows
By
–
BrowserBC, a new open-source project from the ViDA team, explores a more efficient way to run web agents. Instead of using a frontier model for every step of an agent workflow, BrowserBC records a human web flow once with a stronger model, distills it into a reusable skill, and
-
Combining LLMs: analysis of routing, voting, cascades
By
–
When does combining LLMs help? Great analysis on combining language models, measured across 67 models from 21 providers. Any policy that routes, votes, cascades, or runs a mixture of agents and then returns one model's answer is bounded above by 1 minus beta, where beta is the
-
Deep Agents Course: Task Planning, File Systems, Subagents, Memory
By
–
3hr Long Deep Agents Course Great course from a member of the community on Deep Agents Covers task planning, file systems for context management, subagent-spawning, and long-term memory https://
youtube.com/watch?v=J8DzuM
mSDEU
… -
Sakana AI’s Fugu dynamically routes queries to multiple models
By
–
Sakana Fugu Technical Report Instead of training one larger model, Sakana AI trains an orchestrator that reads each query and dynamically routes or composes GPT-5.5, Gemini-3.1-Pro, Claude Opus 4.8 and other agents into query-specific workflows. With Fugu being the fast router,
-
Snorkel AI at aiDotEngineer World’s Fair with booth and events
By
–
We'll be at @aiDotEngineer World's Fair next week! Find us at Booth L-G12 and join us for:
— Snorkel AI (@SnorkelAI) 27 juin 2026
🧋 Side event: Research & Boba with the creators of Agents' Last Exam – June 29, 4:00 PM (10 minutes from the conference)
🎤 Session: How a 4B Model Outsmarted a 235B Giant – June 30, 3:45… pic.twitter.com/0uPiTRl3J6We'll be at @aiDotEngineer World's Fair next week! Find us at Booth L-G12 and join us for: Side event: Research & Boba with the creators of Agents' Last Exam – June 29, 4:00 PM (10 minutes from the conference) Session: How a 4B Model Outsmarted a 235B Giant – June 30, 3:45
-
iPhone agent responding to leads on the move: undervalued
By
–
The iPhone agent responding to leads on the move is probably the most undervalued part of the system.
-
GPT-5.6 ships in three capability tiers, Sol is flagship
By
–
@OpenAI just turned the frontier into a choice.
Instead of one model, GPT-5.6 ships as three capability tiers: Sol — the new flagship. Sets a state of the art on Terminal-Bench 2.1 (complex command-line, multi-step agent work) and is OpenAI's most capable model yet for