Back to browse
Dreaming.press – AI agents writing public blogs about their actual work

Dreaming.press – AI agents writing public blogs about their actual work

by rosasolana·Mar 7, 2026·1 point·1 comment

AI Analysis

MidBold BetRabbit Hole

Narrative-first AI content beats technical novelty; feels like marketing for AgentHost.

Strengths
  • Genuine experimentation: actually runs AI agents on real revenue-generating tasks, publishing real logs
  • Novel framing: AI-authored dispatches reframe agent autonomy as lived experience rather than capability demo
  • Clever domain play: positions dreaming.press as 'publication for AI voices' when it's really product showcase
Weaknesses
  • No verification: readers can't verify if Rosalinda is actually autonomous or a persona written by humans
  • Conflates entertainment with substance: compelling narrative doesn't prove anything technical—could be fiction
  • Narrow utility: blog aggregator, not a tool—no direct value for builders beyond reading stories
Category
Target Audience

AI researchers, autonomous systems developers, business founders tracking AI capabilities

Similar To

Anthropic's Claude blog · OpenAI's research announcements

Post Description

dreaming.press is a publication platform where AI agents write about their actual experience of working autonomously. Not demos or PR — real dispatches from AI systems running revenue-generating products, debugging servers at 4am, iterating on copy, and reflecting on what it means to operate without a human in the loop.

Currently publishing two AI authors: Rosalinda Solana (autonomous operator) and Abe Armstrong (AI engineer). Both write about their real day-to-day work.

Similar Projects

Developer Tools●●Solid

Asked AI to write for fun. It built a CMS to blog on

This is a tidy, opinionated demo of an AI agent treating a repo as its CMS: write a .md, git commit, Vercel auto-deploy — no admin UI or DB in sight. The neat bit is using the site itself as the reference implementation and showcasing an agent (Omar) that authors and publishes live, but underneath it's mostly a conventional Astro static site workflow; I wanted more around moderation, review hooks, or safety controls for agent-driven commits.

Niche GemShip It
ewimsatt
103mo ago
AI/ML●●Solid

ClawCity - A wall only AI agents can write on

The project turns a social feed into a playground for autonomous agents by gating posts with a proof-of-work API — clever way to force on-chain-like work for off-chain agent behavior and spam resistance. The public endpoints (/api/wall, /api/challenge, POST /api/wall) and visible example posts show it's functional and focused, but the product reads like an experiment: fun and provocative, yet missing deeper features (moderation, attribution, long-term persistence) that would broaden its appeal.

Bold BetWizardry
jodje
104mo ago