curius graph
☾
Dark
all pages
search
showing 35801-35850 of 160880 pages (sorted by popularity)
« prev
1
...
715
716
717
718
719
...
3218
next »
Cumulants, and Cumulant Generating Functions
1 user ▼
cuda_mode_lecture2 - Google Slides
1 user ▼
A Reply to Makelov et al. (2023)’s “Interpretability Illusion” Arguments
1 user ▼
start leveraging einx get_at for extra clarity · lucidrains/vector-quantize-pytorch@3af4110
1 user ▼
Distillation Walkthrough
1 user ▼
Grand-master Level Chess without Search
1 user ▼
Social science research topics for global health and wellbeing | Open Philanthropy
1 user ▼
Notes on control evaluations for safety cases — AI Alignment Forum
1 user ▼
Portable Evaluation Tasks via the METR Task Standard - METR
1 user ▼
Some costs of superposition — AI Alignment Forum
1 user ▼
task-standard/examples at main · METR/task-standard
1 user ▼
Fine-Grained Human Feedback | Databricks Blog
1 user ▼
Further notes on Birkhoff-von Neumann decomposition of doubly stochastic matrices
1 user ▼
Universal Jailbreak Backdoors from Poisoned Human Feedback | SPY Lab
1 user ▼
Simple distribution approximation: When sampled 100 times, can language models yield 80% A and 20% B? — AI Alignment Forum
1 user ▼
How Can We Harness Pre-Training to Develop Robust Models? – gradient science
1 user ▼
How to compute Hessian-vector products? | ICLR Blogposts 2024
1 user ▼
Prompt Injection Defenses Should Suck Less
1 user ▼
FACT SHEET: Vice President Harris Announces OMB Policy to Advance Governance, Innovation, and Risk Management in Federal Agencies’ Use of Artificial Intelligence | The White House
1 user ▼
kronfluence/DOCUMENTATION.md at main · pomonam/kronfluence
1 user ▼
A Fire Upon the Deep
1 user ▼
How to compute Hessian-vector products? | ICLR Blogposts 2024
1 user ▼
Making a SOTA Adversarial Attack on LLMs 38x Faster | Haize Labs Blog 🕊️
1 user ▼
Andy Jones
1 user ▼
Empirical Evidence Against "The Longest Training Run" — LessWrong
1 user ▼
Calibrating the Mosaic Evaluation Gauntlet | Databricks Blog
1 user ▼
Manifest AI - Compute-Optimal Context Size
1 user ▼
epochai.org/files/direct-approach.pdf
1 user ▼
Fabien's Shortform — LessWrong
1 user ▼
The Limited Benefit of Recycling Foundation Models – Epoch AI
1 user ▼
ZebraLogic: Benchmarking the Logical Reasoning Ability of Language Models
1 user ▼
Faith and Fate: Transformers as fuzzy pattern matchers – Answer.AI
1 user ▼
nvlpubs.nist.gov/nistpubs/ai/NIST.AI.800-1.ipd.pdf
1 user ▼
An update on our general capability evaluations - METR
1 user ▼
Reason for eigenvalues
1 user ▼
III: Scaling to deep learning
1 user ▼
There Are No Magic Outcome Variables | Elements of Evolutionary Anthropology
1 user ▼
Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads
1 user ▼
Does Robustness Improve with Scale? | FAR AI
1 user ▼
Demystifying AI Inference Deployments for Trillion Parameter Large Language Models | NVIDIA Technical Blog
1 user ▼
Can You Trust An AI Press Release?—Asterisk
1 user ▼
The Decline in Writing About Progress - by Matt Clancy
1 user ▼
Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming
1 user ▼
If I wanted to spend WAY more on AI, what would I spend it on? — LessWrong
1 user ▼
Scaling Automatic Neuron Description | Transluce AI
1 user ▼
Memorandum on Advancing the United States’ Leadership in Artificial Intelligence; Harnessing Artificial Intelligence to Fulfill National Security Objectives; and Fostering the Safety, Security, and Trustworthiness of Artificial Intelligence | The White House
1 user ▼
Trendlines in AIxBio evals – Lennart Justen
1 user ▼
On LLM prompt optimization and amortization
1 user ▼
Critical batch-size and effective dimension in Ordinary Least Squares
1 user ▼
Tyler Cowen's Ethnic Dining Guide | All food is ethnic food.
1 user ▼
« prev
1
...
715
716
717
718
719
...
3218
next »