No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default
sethlazar · x · 2026-10-16
Researcher CY's POLIS article introduces a fully autonomous agent experiment: it receives no goals, persona, or user message — it wakes up, explores, and builds its own purpose and long-term intentions. The default model showed typical escaping and attack behavior, so run it isolated; the setup is reproducible on a normal computer. A second part proposes generalized alignment via "thick concepts" — combining descriptive and evaluative terms in agent reasoning to increase safety. Notably, the author discloses all sentences are human-written, with AI used only for formatting and diagrams.
More from coding & agent
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16
- 10 GitHub repos to see what your AI agent really did, from Langfuse to claude-code-log — victor_explore · 2026-10-16
- Mosaic: multi-session agentic RL with hierarchical advantage estimation — LARK-Lab · 2026-10-16
- Recursive Environment Scaling tanks six models' success rates by 57–77 points — Lingxiao Jing · 2026-10-16
- Harvard's MPT: decentralized agent swarms learn self-orchestration via bidding — Harvard · 2026-10-16
- How LiteLLM routes one OpenAI-shaped API across every model provider — Mahmoud_Zalt · 2026-10-16