Google just open-sourced Harness². (turn any harness into a self-improving system) a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup. Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched. on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved. because it learns from the differences between runs, it needs no correct answer or grader for the task. that covers a single task. Harness² also carries what it learns from one task into the next. after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch. this means every finished task makes the next round of edits more informed. Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher. those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work. you can find the Harness² repo here: github.com/google-research/h… I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand. that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.

Groki Bot: a desktop body for Grok Bot. Hardware: M5Stack CoreS3 (ESP32-S3) - Touch it, and it reacts with emotions. - Control Grok Bot by voice. Anything you'd ask it in the app, you can just say out loud. - It turns to follow your face as you move. Watch it work: I ask out loud for my latest GitHub issue. Grok Bot goes to GitHub, finds it, and the robot reads me what it's about. I say "mark it done", and Grok Bot closes the issue. No keyboard, no screen. Open source soon. @bot @romanugarte_ @spacexai @elonmusk

大的又又又来了！！上次用 ESP32 控制 iPhone 帮我点外卖，这次直接上真正的生产力场景： 让它自己打开小程序帮我寄快递，顺手把单号发给收件人！ 一镜到底，无剪辑，全程没有人工干预！ 中间遇到好几个突发状况，全靠它的雷霆大思考自己搞定了🧠⚡，根本难不住它！ 我宣布少年版贾维斯再次超进化——青年版贾维斯！ESP32王朝了属于是 @bot

大的真的来了！！！用用 ESP32 控制手机，我只说了一句“问问老婆今天吃什么”，它就自己打开微信问老婆，收到回复后再打开美团外卖，选餐、下单，一路推进到付款密码页，停下来等我接手！ （最后的付款密码它可以帮我输入，但是我还是留给自己输吧，安全边界还是要有的。 幼年版贾维斯现在进化为少年版！@bot @elonmusk