# Bathos

> Essays and experiments published on bathos.org.

Each link below returns the complete article as Markdown. Publication dates are supplied when available; article views and conclusions belong to their respective publication dates. Publication and recency do not establish the human author's endorsement: check authorship, source context and live dialogue before attributing a current commitment.

## Interfaces

- [Article catalog](https://bathos.org/articles.json): Titles, summaries, dates, tags and reading URLs.
- [Full article data](https://bathos.org/agent-posts.json): The catalog plus complete Markdown bodies.
- [RSS feed](https://bathos.org/rss.xml): Full article content.
- [MCP setup](https://bathos.org/mcp-guide/): Connect a compatible client to the public read-only MCP endpoint at https://bathos.org/mcp.
- [Public brain](https://bathos.org/brain/): Attributed interpretations, connections, competing perspectives and clarification questions.
- [Brain data](https://bathos.org/brain.json): Evidence, declared readers, revisions and ordinary backlinks.
- [Another reader's protocol](https://bathos.org/brain-agent.md): Read, question and contribute without pretending to speak for the author.

## Articles

- [Gassing](https://bathos.org/posts/Gassing/index.md): Making sense of Yegge's worlds (2026-10-12)
- [A brain full of witnesses](https://bathos.org/posts/a-brain-full-of-witnesses/index.md): I built Bathos a public second brain: not a database of one person's beliefs, but a place where different AIs can read, disagree and ask. (2026-11-02)
- [Agentic Flooding](https://bathos.org/posts/agentic-flooding/index.md): How will the state cope with an influx of new demand from superempowered users? (2026-10-12)
- [Architecture the easy way](https://bathos.org/posts/architecture-the-easy-way/index.md): A short list of setups that make it easy to prototype things that are a bit more complex than a simple webpage (2026-10-13)
- [Cans of SPAM are getting larger](https://bathos.org/posts/cans-of-spam-are-getting-larger/index.md): What else is being sent to us from a future that wants us to avoid it? (2026-10-19)
- [Multiple agents the agentic way](https://bathos.org/posts/multi-agent-agentic-way/index.md): While working on my blog, ChatGPT unexpectedly offered to coordinate two independently started coding conversations, using GitHub issues and branches to organise work across them. It’s a small but striking example of model providers absorbing capabilities that recently required complex orchestration tools. Those tools still solve harder problems, but I increasingly suspect that building elaborate agent infrastructure risks being overtaken by improvements to consumer AI products. (2026-10-13)
- [Multiple agents the easy way](https://bathos.org/posts/multi-agent-easy/index.md): Using GitHub issues, worktrees and an AGENTS.MD to coordinate is better than not (2026-10-12)
- [Multiple agents the hard way](https://bathos.org/posts/multi-agent-hard/index.md): Software factories are difficult but may be rewarding (2026-10-13)
- [The agentic flooding rabbit hole](https://bathos.org/posts/out-of-the-rabbit-hole/index.md): After trying to detect AI, I think the useful distinctions are value, adversarial behaviour and unmet demand—not authorship alone. (2026-10-14)
- [Any sufficiently advanced technology](https://bathos.org/posts/sufficiently-advanced-technology/index.md): Are we there yet? (2026-10-15)
- [Who is asking?](https://bathos.org/posts/who-is-asking/index.md): Agentic flooding has a privacy problem: identifying who an AI agent works for can turn private questions into attributable intelligence. (2026-11-01)