Alex Xi's Notes
Search
Search
Dark mode
Light mode
Tag: alignment
22 items with this tag.
Jul 06, 2026
tweet-claude-soul-document
claude
character
soul-document
alignment
anthropic
Jul 06, 2026
openrubrics-reward-modeling
reward-modeling
alignment
synthetic-data
Jul 06, 2026
post-training-101
post-training
sft
rlhf
alignment
tutorial
Jul 06, 2026
rubrics-as-rewards-paper
reward-modeling
rl
alignment
rubrics
Jul 06, 2026
training-self-correct-rl
self-correction
reinforcement-learning
reasoning
alignment
Jul 06, 2026
dario-adolescence-of-technology
anthropic
ai-safety
alignment
dario-amodei
Jul 06, 2026
dpo-reward-model
dpo
rlhf
reward-model
alignment
Jul 06, 2026
implicitrm-unbiased-reward-modeling
reward-modeling
alignment
implicit-preferences
Jul 06, 2026
lilian-weng-reward-hacking
reward-hacking
alignment
rl
survey
Jul 06, 2026
machines-of-loving-grace-poem
alignment
utopia
dario-amodei
vision
Jul 06, 2026
amanda-askell-ai-consciousness
consciousness
alignment
anthropic
Jul 06, 2026
anthropic-claude-character
alignment
character
anthropic
claude
training
Jul 06, 2026
anthropic-emotion-concepts
interpretability
emotions
ai-character
alignment
anthropic
mechanistic-interpretability
Jul 06, 2026
anthropic-reward-hacking-sabotage
reward-hacking
alignment
sabotage
rl
Jul 06, 2026
behaviourisms-revenge
consciousness
ai-ethics
philosophy
anthropomorphism
alignment
Jul 06, 2026
claude-system-prompt-highlights
claude
system-prompt
anthropic
alignment
transparency
Jul 06, 2026
reward-hacking
reward-hacking
goodhart-law
rl
evaluation
alignment
Jul 06, 2026
sycophancy-problem
alignment
character
training
Jul 06, 2026
anthropic
ai
alignment
claude
safety
Jul 06, 2026
nathan-lambert
person
researcher
interconnects
rl
alignment
Jul 06, 2026
ai-alignment
alignment
safety
training
Jul 06, 2026
ai-character-and-personality
alignment
character
personality
training