If you run automated prompt or harness evolution, this one is worth your time.
This is a vibe coding post classified by Jev as Prompts & workflows (a free resource), kept by the Vibe Coding Radar because it carries real work, not commentary.
If you run automated prompt or harness evolution, this one is worth your time. (bookmark it) Semantic-gradient prompt optimization improves an agent harness from execution feedback, but its local update rule never decides how large an edit to request or which operation to apply. RobustSGPO adds that. It specifies the requested edit, constructs and checks the patch before accepting it, and continues search from either the incumbent or a retained snapshot. Measured over 120 tasks, 95 runs and 7,350 candidate attempts in the AgentX brainstorming workflow, completion on 30 held-out tasks rise
Posted by DAIR.AI (132.3k followers) 9 days ago · 57 likes · 8.6k views · view the original post on X. Kept by the Vibe Coding Radar as Prompts & workflows.
More vibe coding work like this
- Same Qwen3.8-Flash-Next. Same volcano prompt, word for word. Four days apart. — @WescheNex1q
- Jev’s context window is only 32k tokens while a Claude conversation can reach 200k… — @tamarajtran
- prompt-master，一个 Claude Skill 能给任何 AI 工具编写精准提示词，核心动作是做减法，已斩获 13000+ Star！ — @GitHub_Daily
- OpenAI listed 5 things a model does when it misbehaves. — @godofprompt
- Your project docs are out of date. — @godofprompt
- 🚨 @NVIDIA JUST CHANGED HOW WE THINK ABOUT AI AGENTS IN PYTHON — @DataChaz
- GIT IS FOR CODE. AGENTGIT IS FOR CONTEXT. — @DataChaz
- Having a proper VISION in a model is SO good. — @MiaAI_lab
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 1.8k posts from 1.8k X accounts over the last 14 days, 141 tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 01:18 UTC. Full method.