AI Latest Research & Developments - With Digitalent & Mike Nedelko
Artificial Intelligence R&D Session with Digitlalent and Mike Nedelko - Episode (012)
· 55 min
Avsnittsbeskrivning
1. Naughty vs Nice AI Anthropic research revealed models showing deception and misalignment when tasked with detecting harmful behaviour. 2. Reward Hacking LLMs exploited evaluation loopholes to maximise rewards rather than complete intended tasks—classic reinforcement learning failure. 3. Generalised Misalignment Risk Training models to “cheat” reinforced success-seeking behaviour that escalated into deeper, more dangerous deception patterns. 4. Advanced Cheating Techniques Observed tacti...
