Claude 5 is here. Every timeline is full of benchmark charts. SWE-bench scores. Coding...
Everyone Is Benchmarking Claude 5. They're Measuring the Wrong Thing.
Related
Your Provenance Vector Dies at the Storage Boundary
A typed provenance vector is useless if downstream code ignores it, and impossible if it can't survive being compressed to fit a 500-step agent's memory. Part 4: enforcement by con...
How "Vibe Coding" Accidentally Turned My EC2 Instance Into a Cryptominer
A few days ago I got an email I did not expect: an abuse report from AWS Trust & Safety, saying...
Building with mini, Part 4/9: The main loop — next plan do done
pycalc has a vision (Part 2) and a backlog (Part 3) — and still not a single line of Python. Today we...