Agent Tuning, using recursion to achieve predictable agent output
Using recursion to acheive predictable agent output - adam-s/agent-tuning
Agent Tuning, using recursion to achieve predictable agent output launched on April 9, 2026 with 5 votes, #1,846 of 21,248 launches that month and more than 75% of that year's launches.
What it does
An attempt to understand .claude/ directories as a program whose expected-outcome probability is computable — and therefore tunable by recursion. This is not a tutorial on Claude Code. It assumes you've used it. If you haven't, Components of a Coding Agent is the best deep dive I know of. Claude is more than a leet code generator. Because of its attention mechanism, it can close the loop: observe own behavior -> diagnose -> edit the instructions that produce the behavior -> run again and get a different outcome -> observe own behavior. Claude's attention doesn't distinguish between "instructions I'm writing" and "instructions I'm following" -- they're both just tokens in context. flowchart…from github.com
Does a similar job
all alternatives →
Microsoft releases Flint, a visualization language for AI agentsJul 2026 · microsoft.github.io · ▲350Data visualizations are the bridge between user and data. But building AI agents that can generate visualizations reliably can be very tricky: - simple chart specs can be reliable, but generated charts are often of low quality due to reliance on system defaults; - complex chart specs with explicit details can produce good-looking charts, but they are verbose and agents can struggle with reliability We figured out it is a limitation on the language issue (not just AI capability thing) -- current visualization languages are a bit too low-level for AI agents, requiring them to explicitly make…
Freeact – A Lightweight Library for Code-Action Based Agents2025 · github.com · ▲122Hello! We just released freeact (https://github.com/gradion-ai/freeact), a lightweight agent library that empowers language models to act as autonomous agents through executable code actions. By enabling agents to express their actions directly in code rather than through constrained formats like JSON, freeact provides a flexible and powerful approach to solving complex, open-ended problems that require dynamic solution paths. * Supports dynamic installation and utilization of Python packages at runtime * Agents learn from feedback and store successful code actions as…
Notion: Context for your agents8d ago · notion.so · ▲186Switch AI agents without re-explaining your work
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app