The more I talk to agents the more I think that the conversational interface is absolutely not the final destination

Going on two weeks of being super sick, to the point of struggling to get out of bed. Fml 🤦

The polymarket website as seen from greece

Free million dollar idea: `nak` merch take my money.gif, @Gigi

the concept of "subagent" is insanely stupid; hard to believe stuff like this resonates and takes root

A couple days ago these were new shoes

"we have no moat" was google; now its everyone, everywhere, all the time

very interesting; so claude pro & max subscriptions stopped working on TENEX overnight; anthropic api's were responding simply with a generic "ERROR". Turns out that now if the system prompt doesn't identify the agent's name as "Claude Code" it rejects with that generic error. Very lame. Feels straight out of the OpenAI handbook.

privacy-focused like telegram

its 2026 and some people still call context window "memory" *attention* is a much better analogy while working in this neck of the woods I keep thinking of @Gigi for some reason

make wikifreedia contentious again

llms in a loop are not agents what an agent actually is a quasiphilosophical question