Open Questions Dashboard

Generated by _system/lint.py --write-backlog. Do not hand-edit. Harvested from the ## Open Questions section of every concept article. Work #oq/now items (listed in full below) via /query; answered items move to the page's ## Resolved Questions at the next compile.

Full actionable-by-domain / watching / predictions / notes / in-progress bullet lists: Open Questions Backlog.

490 actionable open questions across 234 pages · 114 predictions · 9 notes · 205 in progress · 66 watching (entities), as of 2026-08-19.

Dashboard#

Domain	Actionable	#oq/now	#oq/source	Predictions	Notes	Partial	Median age (d)
agent-systems	98	0	98	21	1	37	16
alignment-and-safety	58	0	58	11	0	24	14
ai-coding-practice	54	0	54	11	0	18	34
ai-economics-and-labor	45	0	45	16	0	7	25
agent-security	42	0	42	1	1	24	34
evals-and-benchmarks	42	0	42	4	0	19	18
superintelligence-trajectory	40	0	40	12	0	27	65
model-capability-and-training	34	0	34	5	2	17	6
startup-founder	24	0	24	12	3	8	88
product-org	24	0	24	9	1	11	47
interpretability	20	0	20	4	1	5	20
formal-math	6	0	6	1	0	0	88
interaction-multimodal	3	0	3	7	0	1	41
(entities — watching)	66					7

Trend: 2026-08-12: 466q/213p → 2026-08-13: 468q/217p → 2026-08-14: 471q/218p → 2026-08-17: 483q/229p → 2026-08-18: 494q/234p → 2026-08-19: 490q/234p

Oldest actionable questions (via git blame):

2026-04-28 (113d) Agent Harness Engineering — At what codebase scale does the AGENTS.md-as-table-of-contents approach need to be replaced with more sophisti…
2026-04-28 (113d) Agent Harness Engineering — How generalizable are these web-app-focused findings to other domains (scientific research, financial modeling…
2026-04-28 (113d) Claude Code Auto Mode — What false-positive rate does the classifier have on routine-but-aggressive refactors (e.g., large-file rename…
2026-04-28 (113d) Claude Code Auto Mode — How well does the classifier generalize to custom tools / MCP servers where it lacks environment context?
2026-04-28 (113d) Claude Code Auto Mode — Does extending auto mode to API users change its calibration — is the classifier retrained for automation-heav…
2026-04-28 (113d) Claude Code Best Practices — How does the Writer/Reviewer pattern compare to agent-to-agent review (as in OpenAI's Codex workflow)?
2026-04-28 (113d) Client-Side Agent Optimization — At what pipeline depth does the combinatorial search become intractable even for Arm Elimination?
2026-04-28 (113d) Client-Side Agent Optimization — What's the right way to re-evaluate when the tool environment changes?
2026-04-28 (113d) Codex App Server Protocol — Is there a public schema registry so external orchestrators can target specific App Server versions without `g…
2026-04-28 (113d) Codex App Server Protocol — The "dynamic tool calls (experimental)" caveat — what's the stability roadmap?