· 3 min read
You probably don't need multi-agent
The orchestrator, the critic, the researcher and the planner walk into your architecture. One model with good tools was already doing the job. The math and the exceptions.
#agents#architecture#cost
5 articles
· 3 min read
The orchestrator, the critic, the researcher and the planner walk into your architecture. One model with good tools was already doing the job. The math and the exceptions.
#agents#architecture#cost
· 2 min read
Frontier output pricing is down roughly 88% since early 2023. The clever cost engineering from two years ago is now complexity you pay to keep.
#cost#architecture#pricing
· 3 min read
Frontier models for frontier problems. For the other 80 percent of your pipeline, a small model at a fifth of the price is not a compromise, it is engineering.
#models#cost#architecture
· 4 min read
Million-token windows did not fix context rot, they subsidized it. How I split the window into line items and stopped my agents from getting dumber mid-task.
#context#agents#architecture
· 3 min read
The Replit incident was not an argument against agents. It was an argument against agents holding production credentials with a pinky promise as the guardrail.
#agents#safety#architecture
get new writeups by email
no schedule, no spam. the next writeup, when it exists.