POSTS

Posts, page 3

Short posts from Anthus on what shipped, what we read, and what changed in AI this week.

2025-05-14#posts
DeepMind's AlphaEvolve evolves programs against an automatic grader. It found a 4x4 matrix multiply with 48 multiplications, and shipped heuristics inside Google.
2025-03-19#posts
METR measures agents by the length of task they can finish, in human hours. That horizon has been doubling about every seven months.
2025-02-24#posts
Claude Code is a research-preview CLI that reads the repo, edits files, and runs the shell. The agent is no longer a chat sidebar. It is a process in the project.
2025-02-20#posts#reading
Vending-Bench asks an agent to run a snack machine for a long time. The hard part is not stocking. It is staying coherent after the twentieth day.
2025-02-03#posts
Voice-driven development with SuperWhisper and Cursor transforms coding into high-level system design, enabling true parallel development streams
2025-01-24#posts
Anthropic's new Citations API enables Claude to provide precise citations for its responses, opening new possibilities for verifiable AI agent systems.
2025-01-21#posts
Perplexity launches Sonar API, packaging their research agent capabilities as a model-like service, following a growing trend of agent-based workflows behind APIs.
2025-01-20#posts#reading
DeepSeek-R1 is not a secret model. It is an open recipe: RL on verifiable rewards, then distill. Frontier reasoning behavior just got cheap to copy.