BOUKOUFFALLAH ABDALLAH·Sep 12Running Local Models Inside CodexConnecting Ollama models to the Codex desktop app
BOUKOUFFALLAH ABDALLAH·Jul 21Speculative Decoding: The Engine Behind Fast LLM InferenceMaking large language models generate faster without making them worse
BOUKOUFFALLAH ABDALLAH·Jun 21Is Claude Mythos a Looped Transformer?From test-time scaling to latent reasoning inside the model
BOUKOUFFALLAH ABDALLAH·Jul 31, 2025Does RL Really Make Language Models Better at ReasoningThe Impact of Data Contamination on RL Training
BOUKOUFFALLAH ABDALLAH·Jun 15, 2025Self-Adapting Language ModelsContinuous Learning For Large Language ModelsA response icon2A response icon2
BOUKOUFFALLAH ABDALLAH·Jun 8, 2025The Illusion of ThinkingUnderstanding the Limits of Large Reasoning ModelsA response icon1A response icon1
BOUKOUFFALLAH ABDALLAH·Apr 28, 2025Test-Time Reinforcement LearningEnhancing Large Language Models Reasoning with RL
BOUKOUFFALLAH ABDALLAH·Apr 26, 2025Welcome to The Era of ExperienceThe Era of Experience: The Next Frontier in AIA response icon1A response icon1
BOUKOUFFALLAH ABDALLAH·Apr 17, 2025Can a Smaller Language Model Outperform a Giant?The Power of Test-Time Scaling