Keep on to blur preview images; turn off to show them clearly
RT @Jimmy_JingLv: 有了 Nano Banana，真的是实现了视频封面自由！ https://t.co/YHY7yOV1bp
🚧 building https://t.co/AJfZ3LMlgq https://t.co/606cFUoda3 https://t.co/s0m0tpQMDH https://t.co/UQ5vrrYdAG 🐣learning/earning while helping others ❤️making software, storytelling videos 🔙alibaba @thoughtworks
If you've been on the fence, try dedicating 10 minutes to make and launch a website with a free .com domain today!
ceo @replit. civilizationist
Then I tell all the other agents working on this project (three Opus 4.5 agents with Claude Code, three gpt-5-codex-max agents in Codex, and three Gemini 3 agents in gemini-cli, all communicating with each other via my mcp agent mail system) the following: "Re-read AGENTS dot md. Be sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages. Don't get stuck in "communication purgatory" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately. When you're really not sure what to do, pick the next bead that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names. Use ultrathink."
Here's another example from just now, but this time just with a single agent (so not using agent mail, although I forgot that in my conversation and confused the hell out of the agent, lol), working on a new tool I'm making that I haven't released yet. I had a bunch of feedback on the current version of the tool that I sort of just brain dumped and then asked the agent to create beads from all those comments. Then once it did that, I asked it to use bv to analyze the beads to determine the optimal order of work: https://t.co/mqVsmy7895
I'm of the position that: 1. Current methods are enough for large scale economic displacement 2. Current methods can scale to AGI/ASI, but there is likely more efficient or optimal ways to achieve it, and those may be invented and implemented before we do the long path with current methods.
Cofounder and Head of Post Training @NousResearch, prev @StabilityAI Github: https://t.co/LZwHTUFwPq HuggingFace: https://t.co/sN2FFU8PVE
My agentic coding workflow has gotten so meta and self-referential lately. I can feel the flywheel spinner faster and faster now as my level of interaction/prompting is increasingly directed at driving my own tools. Like this weird prompt I just used, telling Opus 4.5 to use my beads analysis tool to figure out what all its robot friends should most advantageously apply themselves to using graph theory on my hundreds of open tasks and subtasks in beads: "Re-read AGENTS dot md first. Then, can you try using bv to get some insights on what each agent should most usefully work on? Then share those insights with the other agents via agent mail and strongly suggest in your messages the optimal work for each one and explain how/why you came up with that using bv. Use ultrathink."
Then I tell all the other agents working on this project (three Opus 4.5 agents with Claude Code, three gpt-5-codex-max agents in Codex, and three Gemini 3 agents in gemini-cli, all communicating with each other via my mcp agent mail system) the following: "Re-read AGENTS dot md. Be sure to check your agent mail and to promptly respond if needed to any messages; then proceed meticulously with your next assigned beads, working on the tasks systematically and meticulously and tracking your progress via beads and agent mail messages. Don't get stuck in "communication purgatory" where nothing is getting done; be proactive about starting tasks that need to be done, but inform your fellow agents via messages when you do so and mark beads appropriately. When you're really not sure what to do, pick the next bead that you can usefully work on and get started. Make sure to acknowledge all communication requests from other agents and that you are aware of all active agents and their names. Use ultrathink."
Sometimes y'all make it too easy for the racists, because how do you pull a gun on someone for hariline?
Founder | Author | Speaker Building @beltstripe. Healtech/EdTech/Agric I'm Not The Man Of Your Dreams. Your Imagination Wasn't This Great.