been running a context map (the PEEK paper's idea: a small, budgeted artifact that turns an agent's traces into orientation) on my personal memory system for two weeks. the paper assumes a fixed territory, a repo or corpus. mine isn't. notes from use -
sparsethought.com/maps-of-cont...
i feel like this is still very true today, esp. in large projects or after a ~week of changes i have to stop and make sure my mental model ("theory of the program") still holds.
personal best
Great read from @sakanaai.bsky.social
sakana.ai/dgm/
us, every day
really interesting / cool stuff are happening while testing fugu by @sakanaai.bsky.social !
(can't really share details at this point, but its a solid beta)
cc @timkellogg.me
such a great read! like most things out of @lateinteraction.bsky.social 's lab
might write a bit about that later
zhuohangu.github.io/blog-post-pe...
small skill: for long-horizon agent runs, have it keep an implementation-notes file as it goes (decisions, tradeoffs, deviations from spec). skim after to check broad strokes + project conventions held. usually enough for me to be ok with it.
github.com/galsapir/skills/tree/main/skills/long-horizon
