THE INTERNET IS THINKING
Earlier sources: AI coding agents
AI coding agents use models and development tools to inspect, modify, and test software. Follow coding workflows, repository tooling, evaluations, and evidence about where these systems succeed or fail.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗85 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- Hacker News · Posted on Hacker News · First archived
Show HN: Delegator – Stop juggling coding-agent sessions ↗
I wanted to share Delegator with the HN community. delegator gives you a personal inbox to manage your tasks that is completely local to your machine. Backstory: Like everyone else, I've been experimenting with different AI-assisted development workflows. I realized I was having difficulty with all the context switching between tasks. Asking agents to develop code ends up taking about 5-10 minutes usually for well-scoped tasks. At the beginning I…
- Hacker News · Posted on Hacker News · First archived
Show HN: Agent Squad – Be the CEO of a Claude Code Agent Team ↗
I just released agent-squad for Claude Code and GitHub! You, the human, are the CEO of a team of Claude Code agents: a CTO plans, a developer builds, and QA reviews every pull request. If you work with Claude Code, this will change how you build software forever. It's open source and I'd love to get your feedback.
- arXiv · Published · First archived
How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation ↗
Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quantities separately. Normalized execution relevance determines relative transition support and an effective pseudo-count mass; a Dirichlet posterior then produces an uncertainty-penalized weight for KL-anchored correction learning. Under a symmetric prior, changing mass preserves c…
- Hacker News · Posted on Hacker News · First archived
Show HN: RigMark benchmarks local AI the way coding agents use it ↗
Hacker News discussion.
- GitHub · Repository created · First archived
deeplethe/fde-gym ↗
The harness that runs FDE-Gym cases
- GitHub · Repository created · First archived
flaviocopes/testvm ↗
Run Mac app builds in a headless macOS VM, so coding agents can open, screenshot and click through them without taking over your screen
- GitHub · Repository created · First archived
lastreload/mnemonic-proxy ↗
Like Johnny, your local agent carries more than its head can hold — and keeps working for hours. Transparent proxy: verbatim archive, structured recall, segments, saved engine state.
- Hacker News · Posted on Hacker News · First archived
Show HN: Rashomon – An independent execution record for AI coding agents ↗
I have been working on Rashomon, an open-source execution recorder for AI coding agents. The basic idea is that the agent transcript is not ground truth. Rashomon keeps its own record of what happened and compares it against the agent’s account. For Claude Code, it records things like: * shell commands, exit codes, and whether they may have written files * tool calls and outcomes * test commands and their outcomes * subagent lifecycle and orderin…
- Hacker News · Posted on Hacker News · First archived
Show HN: Usermods, an extension that runs an a coding agent to build userscripts ↗
I built Usermods to make it easy to fix or improve any site on the fly. Remove any user-unfriendly annoyances, get past modal signup screens, or access some sites that otherwise require signup to view content they leave open to be indexed. Or, restyle a site to not look like it’s from last century. Usermods is a browser extension from Chrome, Safari, and iOS that puts a coding agent in your sidebar. Chat with it like you would with Claude and it…
- Hacker News · Posted on Hacker News · First archived
Show HN: Vibivibi – End-to-end encrypted sharing of Coding Agent sessions ↗
Hi HN, I'm Hongyin. I built Vibivibi ( https://vibivibi.com ) because I kept starting a coding agent session on my laptop and wanting to continue it on a server, or hand it to a colleague. I want an easier way to do it but won’t trust anyone hosting my traces who promises they won’t sell it (market price per coding trace is $50 to $100). What Vibivibi does: a small CLI, `vibi`, finds the sessions your coding agents keep locally (Claude Code, Code…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI coding agents
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.