curius graph

all pages

showing 150901-150950 of 200407 pages (sorted by popularity)
[2312.06681] Steering Llama 2 via Contrastive Activation Addition
[2505.05410] Reasoning Models Don't Always Say What They Think
Sub specie aeternitatis - Wikipedia
Huxley family - Wikipedia
Fiat justitia ruat caelum - Wikipedia
LLM Fine-Tuning on a Budget: Top FAQs on Adapters, LoRA, and Other Parameter-Efficient Methods
[2203.02155] Training language models to follow instructions with human feedback
Parameter Efficient Fine Tuning (PEFT) Techniques for Large Models | by Shashank Guda | Jul, 2025 | Medium
Zach Goldman | Portfolio
Rubber Duck Debugging – Rubber Duck Debugging – Debugging software with a rubber ducky
[2406.07882] Designing a Dashboard for Transparency and Control of Conversational AI
Russian cosmism - Wikipedia
Representativeness heuristic - Wikipedia
Lesson 5: Independent Events
[2502.12197] A Closer Look at System Prompt Robustness
Choosing the best AI to do your AI alignment research for you
Does Chat-GPT display ‘Scope Insensitivity’? — LessWrong
SearchQ AI
Nebius. The ultimate cloud for AI explorers
SearchQ AI
Search Flights, Hotels & Rental Cars | KAYAK
Transformers
Trainer
Adapters
Hugging Face - Wikipedia
huggingface/safetensors: Simple, safe way to store and distribute tensors
Psychological Science-2013-Finkel-0956797612474938.pdf
Hussein Lezzaik blog
Amazon.com: Choices, Values, and Frames: 9780521627498: Kahneman, Daniel, Tversky, Amos: Books
Prospect theory - Wikipedia
[2406.08464] Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
GRPO Trainer
Anthropic Economic Index: Tracking AI's role in the US and global economy \ Anthropic
Persona vectors: Monitoring and controlling character traits in language models \ Anthropic
“If Anyone Builds It, Everyone Dies” release day! — LessWrong
Meet the Extropians | WIRED
How Peter Thiel’s Relationship With Eliezer Yudkowsky Launched the AI Revolution | WIRED
A.I.’s Prophet of Doom Wants to Shut It All Down - The New York Times
Frame analysis - Wikipedia
Social identity theory - Wikipedia
Social identity threat - Wikipedia
Defensive help - Wikipedia
R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning
The Future of Machine Intelligence
AGI House
[1807.03748] Representation Learning with Contrastive Predictive Coding
Conversation Café | Conversations that Matter!
Bytecode - Wikipedia
Papers — Future of Humanity Institute
Flywheel