New Tool Lets You Search and Skim Anthropic's Released Mythos Transcript by Flagged Behaviors
round · x · 2026-09-18
- MatthewWSiu built an investigation tool for Anthropic's released Mythos transcript.
- It supports keyword/prompt search across the transcript.
- Results are shown with surrounding context "squished" for fast skimming.
- It also gives an overview of flagged behaviors and jumps to key passages in context.
More from Research
- SPLADE's original author releases new sparse embedding model: 150M params beat models up to 1B — IgorCarron · 2026-09-18
- Chinese Researchers Open-Source Cache-to-Cache: LLMs Talk Without Tokens, +14.2% Accuracy — Scobleizer · 2026-09-18
- Xiaomi MiMo achieves streaming large-scale LLM RL training, including a 1T-parameter model — stanfordnlp · 2026-09-18
- Anil Seth's Conscious AI and Biological Naturalism collection out in BBS with fifty commentaries — anilkseth · 2026-09-18
- Jev as an LLM judge flops: scores nearly everything positively, disagrees with humans — amplifiedamp · 2026-09-18
- Open-Source Dexterous Astra: Zero-Shot Pen Spinning and One-Handed Rubik's Cube in Sim — ZeYanjie · 2026-09-18