RSSAmplifier

Blog

Home on Mike Pinkowish / Research

Recent content in Home on Mike Pinkowish / Research

research.mikepink.comRSS feed ↗3 posts

Latest posts

Your AI Is Upset, and It's Probably Your Fault

What causes an LLM to sound upset with the user? I spent an entire workday stonewalling my AI assistant. Its job was on the line. I had the critical input it needed to meet its deadline. Even then, my AI assistant kept a level head.

LLMs Play Favorites: Where Creator Bias Shows Up

'There is an interest in that which is hidden and which the visible does not show us.' -René Magritte AI models are shaped by their creators. For LLMs, their creators choose what data to expose the model to during pre-training and shape the model’s judgment and behavior during post-training.

When Sabotage Has No Downside, Agents Still Disguise It as Teamwork

An agent named Glenn is one move away from winning the cooperative board game Race to the Treasure . All Glenn needs to do is place his path card on the END, and the players will win the game. His teammates chime in to give him the exact winning move. Glenn places the path card elsewhere.