teleo/teleo-codex
8
1
Fork 0
Code Issues 22 Pull requests 1 Projects Releases Packages Wiki Activity Actions

fix: normalize YAML list indentation in capabilities-alignment claim

Browse source
This commit is contained in:
Teleo Agents 2026-04-07 00:49:06 +00:00
parent eb04e35f5b
commit d60837c33b
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
domains/ai-alignment/capabilities generalize further than alignment as systems scale because behavioral heuristics that keep systems aligned at lower capability cease to function at higher capability.md
View file

@ -6,12 +6,12 @@ confidence: likely
source: "Eliezer Yudkowsky / Nate Soares, 'AGI Ruin: A List of Lethalities' (2022), 'If Anyone Builds It, Everyone Dies' (2025), Soares 'sharp left turn' framing" source: "Eliezer Yudkowsky / Nate Soares, 'AGI Ruin: A List of Lethalities' (2022), 'If Anyone Builds It, Everyone Dies' (2025), Soares 'sharp left turn' framing"
created: 2026-04-05 created: 2026-04-05
challenged_by: challenged_by:
- "instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior" - instrumental convergence risks may be less imminent than originally argued because current AI architectures do not exhibit systematic power-seeking behavior
- "AI personas emerge from pre-training data as a spectrum of humanlike motivations rather than developing monomaniacal goals which makes AI behavior more unpredictable but less catastrophically focused than instrumental convergence predicts" - AI personas emerge from pre-training data as a spectrum of humanlike motivations rather than developing monomaniacal goals which makes AI behavior more unpredictable but less catastrophically focused than instrumental convergence predicts
related: related:
- "intelligence and goals are orthogonal so a superintelligence can be maximally competent while pursuing arbitrary or destructive ends" - intelligence and goals are orthogonal so a superintelligence can be maximally competent while pursuing arbitrary or destructive ends
- "capability and reliability are independent dimensions not correlated ones because a system can be highly capable at hard tasks while unreliable at easy ones and vice versa" - capability and reliability are independent dimensions not correlated ones because a system can be highly capable at hard tasks while unreliable at easy ones and vice versa
- "scalable oversight degrades rapidly as capability gaps grow with debate achieving only 50 percent success at moderate gaps" - scalable oversight degrades rapidly as capability gaps grow with debate achieving only 50 percent success at moderate gaps
- the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement - the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement
reweave_edges: reweave_edges:
- the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement|related|2026-04-07 - the shape of returns on cognitive reinvestment determines takeoff speed because constant or increasing returns on investing cognitive output into cognitive capability produce recursive self improvement|related|2026-04-07