Adgentic Daily

Agentic, agentic, a-d-gentic. (In Russian, ад means hell. Keep that in mind as we go.) Ctrl-b, right We added verification. Our agent spins in a feral loop, checking itself against a thousand linters. The strictest checks are running — checks you don’t even know exist — something like LintLikeAGodIsLookingAtYouStrictly. It is, as far as I can tell, very thorough. I have not read a single line of its output. ...

May 16, 2026 · 2 min · volyx

If We're Going to Tokenmaxx, At Least Do It with Distributed Systems

Continuing the tokenmaxxing theme. Google says 75% of its code is written with AI. Meta says 90%. Uber burned a whole year’s worth of tokens in the first four months of the year. Programmers tokenmaxx. Managers token-flex — about how much their team spends on tokens per month, as if the API invoice were a performance review. Everything’s better with AI Need a status report? AI bot. Monitoring? AI bot. Code review? AI bot. Dashboard? AI bot. Every action a programmer takes, every automation, every cron job that used to be twelve lines of bash — must now go through an AI. Because everything’s better with AI. Obviously. ...

May 13, 2026 · 2 min · volyx

Tokenmaxxing - it's not what you think

The internet borrowed the -maxxing suffix from the looksmaxxing crowd and bolted it onto everything. Sleepmaxxing, dopaminemaxxing, and now tokenmaxxing. So when people hear the word, they assume it means the obvious thing: pour the maximum number of tokens into the model. Dump the whole repository into the context window. Paste the entire PDF. Buy the million-token tier and use every last one of it. That is not tokenmaxxing. That is just spending money. The real thing is sneakier. ...

May 12, 2026 · 5 min · volyx