curius graph
☾
Dark
all pages
search
showing 4651-4700 of 198841 pages (sorted by popularity)
« prev
1
...
92
93
94
95
96
...
3977
next »
Eliciting Latent Knowledge - Google Docs
4 users ▼
[2601.21571] Shaping capabilities with token-level data filtering
4 users ▼
[2601.19062] Who's in Charge? Disempowerment Patterns in Real-World LLM Usage
4 users ▼
A Straussian reading of The Adolescence of Technology | Zhengdong
4 users ▼
Intentionally Designing the Future of AI
4 users ▼
In (highly contingent!) defense of interpretability-in-the-loop ML training — AI Alignment Forum
4 users ▼
[2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMs
4 users ▼
[2512.24601] Recursive Language Models
4 users ▼
[2505.10831] Creating General User Models from Computer Use
4 users ▼
College at Age Sixteen: What Is Intelligence For?
4 users ▼
None of us are easy to be with - by hasif 💌
4 users ▼
How AI assistance impacts the formation of coding skills \ Anthropic
4 users ▼
Best Of Moltbook - by Scott Alexander - Astral Codex Ten
4 users ▼
Life on Claude Nine - Igor Babuschkin
4 users ▼
How to increase your surface area for luck - by Cate Hall
4 users ▼
what makes a person interesting? - by emily north
4 users ▼
Text is king - by Adam Mastroianni - Experimental History
4 users ▼
Anthropic’s “Hot Mess” paper overstates its case (and the blog post is worse) — LessWrong
4 users ▼
Chemical hygiene | karpathy
4 users ▼
The Easing Blueprint
4 users ▼
[2512.23675] End-to-End Test-Time Training for Long Context
4 users ▼
Philosophy behind Claude's Constitution
4 users ▼
it's time to start bullying young Palantir employees
4 users ▼
[2501.16946] Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development
4 users ▼
Survival without dignity - Rudolf's Writing
4 users ▼
You're overspending because you lack values
4 users ▼
Insights on Crosscoder Model Diffing
4 users ▼
Design Waterloo
4 users ▼
stanford-steam-tunnels.pdf
4 users ▼
Being creative requires taking risks - by Henrik Karlsson
4 users ▼
[2512.18792] The Dead Salmons of AI Interpretability
4 users ▼
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
4 users ▼
A common type of time sink - by Alex - Cognition Café
4 users ▼
Free Online PCB CAD Library | Ultra Librarian
4 users ▼
Iris
4 users ▼
What stops me from writing | Kat Huang
4 users ▼
Gödel, Escher, Bach
4 users ▼
hyam is designing...
4 users ▼
Home - informal
4 users ▼
turntrout.com/alignment-phd
4 users ▼
Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Models
4 users ▼
naturalhazard.xyz/ben_jess_sarah_starter_pack.html
4 users ▼
Factory | Agent-Native Software Development
4 users ▼
Afterimage
4 users ▼
Public Work by Cosmos
4 users ▼
Streisand effect
4 users ▼
Shipmap.org | Visualisation of Global Cargo Ships | By Kiln and UCL
4 users ▼
dreamofmachin.es/machine_prophecy.html
4 users ▼
Galois - Specifications Don't Exist
4 users ▼
Can we safely automate alignment research? - Joe Carlsmith
4 users ▼
« prev
1
...
92
93
94
95
96
...
3977
next »