curius graph

all pages

showing 151151-151200 of 200407 pages (sorted by popularity)
[2501.11183] Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
HAI research areas | University of Technology Sydney
‪David Williams-King‬ - ‪Google Scholar‬
UKGovernmentBEIS/control-arena: ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
UKGovernmentBEIS/control-arena: ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
Notion
Ari Brill
Computational Complexity as an Intuition Pump for LLM Generality | Ari Brill
Investigating Neural Scaling Laws Emerging from Deep Data Structure — LessWrong
[2209.10652] Toy Models of Superposition
[2407.15549] Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
zhu-minjun/PAlign: Personality Alignment of Language Models
The Overstory - Wikipedia
Harry Law
Talking Nets
Philosophy Bites Podcast
Genius Makers: The Mavericks Who Brought AI to Google, Facebook, and the World, Metz, Cade, eBook - Amazon.com
Empire of AI - Wikipedia
Sam Marks's Shortform — LessWrong
Role embeddings: making authorship more salient to LLMs — LessWrong
The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models — LessWrong
Home
Viewcy | Ed Malone
[1908.08881] Complexity and Geometry of Sampling Connected Graph Partitions
Elle Najt's webpage
[2509.17567] LIMI: Less is More for Agency
[2510.04618] Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Mental software updates | world spirit sock puppet
Alignment Fine-tuning is Character Writing
Notes_on_Coherence_Optimization.pdf - Google Drive
Dezhi Luo – What is a site tagline?
GrowAI
Not-Just-Scaling Laws
Computational theory of mind - Wikipedia
Neuro-Symbolic Models of Human Moral Judgment: LLMs as Automatic Feature Extractors | OpenReview
The Blablablab
The Mental Representation of Human Action
Poseidon Research
JustinShovelain — LessWrong
Aligned AI / Blog
[2307.15217v2] Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
About | Dave Banerjee
University EA Groups Need Fixing | Dave Banerjee
Fog of war - Wikipedia
AE Studio | Custom Software Development
AE and AI Alignment
AE Studio Blog - AE Studio
[2507.02092] Energy-Based Transformers are Scalable Learners and Thinkers
[2307.07697] Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
ReNorM: Aligning AI Requires Automating Reasoning Norms by Aidan Kierans :: SSRN