Prime Radiant 团队在构建内部 AI 工程师 Ada 的过程中,发现单纯赋予代码执行能力(如 gh cli)不够,需要引入“治疗师模式”。该模式强调在让 AI 代理处理复杂任务前,先通过对话梳理其逻辑状态、排查认知偏差或上下文混乱,类似人类工程师的代码审查与结对编程。这揭示了当前 Agentic AI 开发中,从“自动化执行”向“协作式推理”转变的关键工程实践,为解决 AI 幻觉和逻辑死循环提供了新思路。
I'm pleased to announce Superpowers 5.1.0. The biggest changes in this release are: • A reworking of how we use git worktrees, now that Claude Code and Codex have first-class support for them. • Re...
Work gets better when it's reviewed after completion. That's at least as true for agentic work as it is for human work. Many moons ago, Harper taught me a cute trick for getting an agent to think cri...
Last fall I had a bit of a problem with Claude. It was deleting tests. First, I caught it removing a single assertion from a test file. The next day, it deleted an entire test file from an active p...
Crossposted from Prime Radiant's blog – I'm really excited about all of the stuff we are doing at Prime Radiant. For the most part we're blogging about it over there, but I'm going to continue to lift...
One of the first things I stumbled into as I was building what became Superpowers was the idea of a "gate" in a prompt. It's a term that Claude Code introduced me to, so clearly was part of the liter...
Over the past couple of months, Superpowers has gotten popular. Like really popular. It now has over 120,000 GitHub stars. That's more than 100x as many stars as my second-most-popular project, and pu...
One of the things that keeps coming up in my conversations about AI and software is the difference between software with an agent or LLM in the loop and what we've always thought of as "software". It...
Superpowers 5 is out today. Visual Brainstorming # By far, my favorite new feature is the "Visual Brainstorming" companion tool, which grew out of my frustration with the ASCII art that Claude usua...
Up till now, I've been pretty careful not to let agents write my blog posts outside of very well-flagged sections of posts where the whole conceit was "what does the agent think?" One of the wildest t...
I've realized that I have two primary ways that I'm building software with AI. The first is the one that Superpowers excels at. I'll spend a significant amount of time up front thinking through exact...
Last night, I had dinner with a friend from college. She's now a university professor. After catching up about our families and what we've been up to over the last couple of decades, the conversation...
] If you've been following consumer uptake of AI agents over the past few weeks, it will have been hard to miss Clawdbot (now known as Openclaw). Clawdbot is, essentially, an AI agent that runs in yol...
A lot of the focus on interacting with agents recently has been on "context engineering," which is the discipline of packing exactly the information that the agent needs to know into the prompt. Conte...
When cryptocurrencies first became a thing, some of their loudest proponents talked about how they were free, democratic, and open, and didn't need all of the regulation and bureaucratic institutions ...
My all-time favorite word game is called 'Wordiest'. It was an earlyish Android game with a pretty simple mechanic: You get 14 Scrabble-style tiles and need to make the two highest-scoring words you c...
I woke up this morning to discover that, without my knowledge or consent, someone had created an ICO using the Superpowers name and my Twitter username. They emailed me excitedly to tell me that I'd a...