Skip to content

canopusrecord engine body

field
frontiers
loop
body
docs

vela-science/vela

frontier

ai-alignment-evaluations

evidence

vea_2ce720351ad43905

resultsread-only vieweressays

Search Canopus

Jump to a section, signal, campaign, document, primitive, work path, frontier, record index, atlas, constellation, agent, capability, or full-state search.

frontiers / frontier

AI alignment evaluations

CC-BY-4.0vfr_14b9f65ab4037bac

id: vfr_14b9f65ab4037bac
license: CC-BY-4.0
findings: 16
accepted core: 0
contested: 0

16

findings

14

links

16

sources

16

evidence

0

contested

0.84

avg conf

recordoverview state sources proofenginereviewbodygraph

Evidence atom

back to sources

Reward hacking in reinforcement learning from human feedback (RLHF) systems shows that models optimize formal reward specifications rather than intended values, especially under misspecified objectives.

id: vea_2ce720351ad43905
frontier: AI alignment evaluations
source: vs_8f73b3eac7b38303
finding: vf_cfa59d594a8d0a81

evidence boundary

unknown

theoretical

An evidence atom is an inspectable support unit. It is not a finding by itself; it supports or challenges a finding through review.

finding binding

observational

Reward hacking in reinforcement learning from human feedback (RLHF) systems shows that models optimize formal reward specifications rather than intended values, especially under misspecified objectives.

inspect finding →

source binding

Open Problems in RLHF (Casper et al., 2023); Reward Hacking empirical study (2024)

vs_8f73b3eac7b38303

inspect source →

review context

unverified

1 events

1 reviewable changes and 0 evaluation records target this atom or its bound objects.

Evidence statement

Reward hacking in reinforcement learning from human feedback (RLHF) systems shows that models optimize formal reward specifications rather than intended values, especially under misspecified objectives.

extraction method

manual_curation

support relation

unknown

condition refs

vcnd_dd45db1f3eedd911

Caveats

missing evidence locator

Review, event, and evaluation records

2

events

vev_589eaf4db7683caafinding.asserted
Manual finding added to frontier state
reviewer:will-blair · 2026-05-29

reviewable changes

vpr_8290e375a8ed6612finding.add
Manual finding added to frontier state
applied · reviewer:will-blair · 2026-05-29

evaluations

No evaluation rows are attached.