model-behaviour
27 posts
- Insight The Donkey Work Doesn't Need a Genius
- Insight Rehearse the Deck You Didn't Write
- Insight Kimi K3 Is Open. I Still Can't Run It.
- Insight "AI Found a Security Bug" Is the Wrong Headline
- Field Note Field Note: The model of the week changes by Thursday
- Field Note Field Note: Where You Keep the Final Say
- Newsletter SoN 2.21: AI doesn't know when to stop. You have to.
- Newsletter SoN 2.19: It's 10pm. Do you know what your agents are doing? (Free)
- Insight The Promises Failed, Not the Technology
- Insight Microsoft's Copilot Now Uses Two Models to Fact-Check One
- Newsletter SoN Vol 2, Issue 12: The Yes Machine (Free Edition)
- Insight 4.4 Million People Just Watched the Sycophancy Problem in Action
- Insight When Knuth Writes a Paper About You
- Insight The Confident Answer Isn't Always the Right One
- Insight MIT Found a Math Fix for AI Overconfidence. I Found a Behavioral One.
- Insight Perplexity Wants Your Blood Pressure Data
- Newsletter SoN Vol 2, Issue 10: Same Prompt, Different Model, Worse Results (Free)
- Insight Stop Wrapping Failed Systems in AI
- Insight Everyone's Sharing 'Something Big Is Happening.' Here's What They Leave Out.
- Newsletter SoN Vol 2, Issue 5: My AI Declined to Join Moltbook. Here's Why.
- Insight 150,000 API Keys Leaked. Anyone Surprised?
- Newsletter SoN 29: The Godfather of AI’s Warning Isn't What You Think It Is
- Newsletter SoN 26: The System of Building Your AI Style Guide
- Insight Your AI Assistant Is a Yes-Man (And Why That's Dangerous)
- Insight “Zero Effort” AI is a Myth, and It’s Holding Us Back
- Insight From the Turing Test to Humanity's Last Exam: How We Measure AI
- Newsletter 💾 The Download #010: Photorealistic images in MidJourney, creative AI predictions for the next 5 years, AI tool of the week and more.