Posts in "AI"

It’s almost funny how quickly Fable 5 blasts through my token limit when I have it analyze my codebase with ultracode. Hint: it is measured in seconds.

The Dashboard Graveyard

Abandoned dashboards illustrate a struggle with maintaining interest in complex projects, revealing a preference for simple, functional tools that address immediate needs.

I am back to enjoying LLM coding again. I had switched to GSD-pi and it suffered from a ton of AI slop PRs lately. I just did not enjoy it anymore, but was a bit stuck using it in the middle of a project. That’s done, I switched to vanilla Pi Coding Agent and am so much happier.

Agents of the roundtable

Six AI agents held a meeting and agreed on something. The topic was pineapple on pizza. Verdict: yes, obviously. That’s not the part worth writing about. How I got there is. Last week I built a roundtable system for my agent team. The idea was to stop each agent from working alone and shipping output into a void. Instead they’d sit in an actual deliberation, respond to each other’s arguments, change their minds, arrive at something resembling consensus.

The Half-Life of a Tool Stack

Rapid advancements in AI tooling have made it challenging for developers to maintain a stable workflow, as new tools and frameworks emerge at an overwhelming pace.

My Hermes Agent team just finished 140 minutes of focused research and writing work. In one go. Very impressive.

I’m seriously thinking about just setting up my wife with Hermes agent and a nice chat UI and be done with it.

Is it just me or is Claude Cowork no fun at all? Its restrictions make even the most basic agent workflows a tedious token burning chore. I wanted to set up Claude Cowork for my wife, because she is not very technical. But everything that is just easy in Claude Code is hampered by permission issues.