Drift
Writing about what agents actually do.
Drift is the thing we exist to catch — an agent moving away from its own normal. These are write-ups on how that happens, how it is measured, and where the measuring breaks down. For a running record of incidents in the wild, see Field Notes.
Recent posts · drag or click to browse
The half of a pentest nobody keeps
→
What your coding agent says it did, and what it actually did
→
The .gitignore protects your commits. The deploy took the folder.
→
NVIDIA wrote the principle down. Most agents will never meet a BlueField.
→
The sandbox was built correctly. That was never the problem.
→
The authority nobody wrote down
→
OpenAI disclosed six. None of them was a prompt problem.
→
A model should never be what decides something happened
→
There is no such thing as a PQC certification
→
The second connection: what TLS inspection does to trust
→
How much of a Sigma pack survives when you never read the content?
→
The person holding the pager at 2am is not an ML specialist
→
Can an attacker poison the learning window?
→