Human curiosity, technology support
A note on how this site is made, the tools involved and editorial responsibility.
Writing on research, making and observation.
A note on how this site is made, the tools involved and editorial responsibility.
On Nage AI OS and SEDIM: knowledge, evidence and the questions we can ask afterwards.
The boundaries between AI interface suggestions, permission to perform operations and human control, through Muhit.
How decisions about drafts, focus, errors, cancellation and themes take shape in Muhit’s working examples.
Visual language, page states, preserved context and the promise an interface makes, through the work on Muhit.
Inputs, file identities, evidence and the limits of human evaluation through ERM v0.12’s dated validation records.
From an ADL experiment that missed its target to Evidrel’s decision traces: keeping expectations, observations and later explanations distinct.
Source, scope and review decisions: how a correction preserves an old record and changes its subsequent use in Evidrel’s local research notebook.
Stopping before execution when a skill version changes in the a2 demo, and the distinction between code identity and correctness.