Back to article
stevekinney.com

Some Thoughts on AI Safety (opens in new tab)

Covers 11 stories See all stories this covers including Goodhart's LawDiscussed on Hacker News

Covers 11 related stories

Wikipedia·

Goodhart's Law

Discussed on Hacker News and Hacker News
Feeds
Dario Amodei·

Machines of Loving Grace

Discussed on Hacker News and Hacker News
Feeds
Wikipedia·

Seeing Like a State

Discussed on Hacker News
Feeds
Dario Amodei·

The Urgency of Interpretability

Discussed on Hacker News and DEV
Feeds
Anthropic·

https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback

Feeds
Wikipedia·

Streetlight Effect

Discussed on Hacker News
Feeds
Anthropic·

Core Views on AI Safety: When, Why, What, and How

Discussed on Hacker News
Feeds
donellameadows.org·

Leverage Points: Places to Intervene in a System - The Donella Meadows Project

Feeds
arXiv·

Beyond 'Is It Intelligent?': A 5-Layer Framework for Understanding What LLMs Actually Do

Discussed on DEV
Feeds
Anthropic·

Activating AI Safety Level 3 Protections

Discussed on Hacker News
Feeds

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help