AI Latest Research & Developments - With Digitalent & Mike Nedelko
Dillan Leslie-Rowe
6 episodes
1 month ago
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...
All content for AI Latest Research & Developments - With Digitalent & Mike Nedelko is the property of Dillan Leslie-Rowe and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
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...
Artificial Intelligence R&D Session with Digitlalent and Mike Nedelko - Episode (012)
AI Latest Research & Developments - With Digitalent & Mike Nedelko
55 minutes
1 month ago
Artificial Intelligence R&D Session with Digitlalent and Mike Nedelko - Episode (012)
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...
AI Latest Research & Developments - With Digitalent & Mike Nedelko
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...
