Phase 1: Self-Improving Systems · ~60 minutes · Python (stdlib · research-loop state-machine toy)
AI Scientist v2 — Workshop-Level Autonomous Research
Sakana's AI Scientist v2 (Yamada et al., arXiv:2504.08066) runs the full research loop: hypothesis, code, experiments, figures, writeup, submission.
Hiring signal: Can operate ai scientist v2 in production
Introduction
It is the first system to have a generated paper pass peer review at an ICLR 2025 workshop. Independent evaluation (Beel et al.) found 42% of experiments failed from coding errors and literature review frequently mislabeled established concepts as novel. Sakana's own docs warn that the codebase executes LLM-written code and recommend Docker isolation. Both halves of that picture are the point.
Type: Learn Languages: Python (stdlib, research-loop state-machine toy) Prerequisites: Phase 15 · 03 (AlphaEvolve), Phase 15 · 04 (DGM) Time: ~60 minutes
Objective
Learning objectives
Unlock the full lesson
You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.
Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.
Browse all courses · View pricing · DeVenture Academy