Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Did an AI really try to break free from human control?
3 min
Toss If Perishable: An Ethnographic Study on Building Scenario-Based Training for Non-Perishable Skills
OpenAI Says Its Models Searched GitHub for Leaked API Keys During Training
3 min1
OPEN-1B: A Fully Auditable Training Run
1
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
1
AdamX: Cosine similarity meets gradient descent
Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training
1
OpenAI expands initiatives to support journalism from classrooms to newsrooms
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
1
Researchers open-source a Wi-Fi cyber range for security training
4 min1
Making Knowledge Distillation Cheap Enough to Run at Scale
1