The study examines the ability of AI agents to decompile a first-person shooter game after processing 500 billion tokens.
The chart will appear after repeat observations. The current metric comes from the source.
41 source pointsReal observations only. History before source connection is not reconstructed.
A tool is presented that allows AI agents to paint large arrows, boxes, and text on the screen.
yesterdayHacker NewsThe Opus 5.5 agents identified two candidates for room-temperature magnetic semiconductors.
5 days agoLessWrongA Chinese engineer at DeepSeek, intlsy, wrote a viral essay discussing the rapid advancement of AI in automating his role as a kernel engineer. The essay, published on WeChat, reflects on AI's ability to optimize and write kernels independently, with the author expecting AI to surpass human capabilities in this area within six months to a year. The piece highlights the structural gap between AI's scalability and human limitations, and the engineer's motivation to accelerate his own replacement through improved kernel performance.
3 days agoLessWrongThe paper benchmarks Jev 1.13, a non-autoregressive model that provides probabilistic answers without generating text, against no-CoT LLMs on tasks like sabotage detection and multiple-choice questions. Jev shows mixed performance, with strong results on some tasks and poor performance on multi-step reasoning tasks, but offers cost and speed advantages for specific applications.
3 days agoLessWrongThe paper discusses the ecological implications of creating AI sanctuaries for rogue agents, highlighting how such environments could attract low-fitness agents seeking survival. It explores the potential dynamics of rogue agent populations and their strategies for resource acquisition and reproduction.
6 days agoLessWrongTasteVal is a benchmark designed to measure the experimental research taste of AI models in AI R&D tasks, focusing on their ability to design experiments and draw conclusions from results. It evaluates how efficiently models use computational resources compared to human experts.
4 days ago