AI Alignment

Feeds to Scour
SubscribedAll
Scoured 72 posts in 10.0 ms

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

 🧠LLMs  Content type: Academic
arxiv.org·

Mechanistic Interpretability: The Key to Trusting Agentic AI

 🧠LLMs  Content type: Discussion
bradenkelley.com·

The Ghost of Alignment — Why AI Should Never Fully Obey Humanity

 📊AI Monitoring  Content type: Blog
medium.com
·

[Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"

 🧩Epistemics  Content type: Blog

Sequent: scale and automation for higher confidence in alignment

 🧠LLMs
lesswrong.com·

How authoritarian governments twist AI safety to coerce tech companies to comply

 📊AI Monitoring
fastcompany.com·

Criti-hyping is the best thing that happened to Big Tech

 📝Long-form Essays
reveriesofahuman.com·

Controversial smut as an AI alignment issue

 🧩Epistemics  Content type: News  Content type: Blog

Why LLMs (still) lack taste

 🧠LLMs

The crucial human component in computing and AI

 🧩Epistemics  Content type: Academic
news.mit.edu·

Solsong Chord Updates

 🧠LLMs
jefftk.com·

Reasoning RL in 2026: GRPO, DPO, RLVR, Agentic PO & Beyond

 🧠LLMs
turingpost.com·

Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

 ⚙️AI Infrastructure  Content type: Academic
arxiv.org·

Op Ed: Consultant Tony O’Connor On The Agentic Trojan Horse

 📊AI Monitoring
thecompanydime.com·

scMTG reconstructs single-cell temporal dynamics with Markov transition generators

 🧠LLMs  Content type: Academic
biorxiv.org·

Stack Overflow didn't just help AI learn to code

 🧠LLMs
Less-relevant results

Complete Drosophila Nervous System Mapped

 ⚙️AI Infrastructure
neurosciencenews.com·

The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably

 🧩Epistemics
lesswrong.com·

Why Claude Produces High-Quality Output: A Developer’s Guide to Token Efficiency and Hallucination…

 📡Information Retrieval  Content type: Blog
medium.com·

Designer babies. Self-improving AI. Are we ready for either?

 🧩Epistemics  Content type: News
vox.com
·

Keyboard Shortcuts

Navigation

Next / previous item
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
Browse
gb
Search
/

General

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

Press ? anytime to show this help