Sitemap - 2024 - Daniel Paleka's Newsletter

September/October 2024 safety news: Jailbreaks on robots, Breaking unlearning, Forecasting evals

July/August 2024 safety news: Tamper resistance, Fluent jailbreaks, Scaling limits

May/June 2024 safety news: Out-of-context reasoning, Sparse autoencoders, Interpreting CLIP

March/April 2024 safety news: Latent training, Emergent abilities, Instruction hierarchy

January/February 2024 safety news: Sleeper agents, In-context reward hacking, Universal neurons

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts