Sign in Subscribe

alignment

May
01
ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)

ORPO: Monolithic Preference Optimization without Reference Model (Paper Explained)

🆕 from Yannic Kilcher! Discover how ORPO simplifies preference optimization by integrating supervised fine-tuning and alignment steps into a unified procedure,
3 min read
Dec
14
How To Stop Procrastinating For Good - Ali Abdaal

How To Stop Procrastinating For Good - Ali Abdaal

🆕 from Chris Williamson! Discover how feeling good can enhance your productivity and creativity. Find out why making tasks enjoyable is
8 min read
Dec
14
GPT-4.5 Leaks (some fake) Plus OpenAI on AI Safety

GPT-4.5 Leaks (some fake) Plus OpenAI on AI Safety

🆕 from Wes Roth! Rumors and speculation surround the release of GPT-4.5, while OpenAI makes real announcements on AI safety
2 min read