Original Academy
Legacy mirror · noindex · upstream phase 15
Autonomous Systems
Long-horizon agents, self-improvement, and the 2026 safety stack.
Provenance: this phase outline and its lesson readings are preserved from ai-engineering-from-scratch by Rohit Ghumare under the MIT License. InterviewsVector does not claim authorship. These archive pages remain available for old links and progress, but are excluded from indexing.
Attributed readings
- 01From Chatbots to Long-Horizon Agents (METR)In 2023 a chatbot answered a question in one turn. In 2026 a frontier model routinely runs minutes to hours on a single task. METR's Time Horizon 1.1 benchmark (January 2026) pu…
- 02STaR, V-STaR, Quiet-STaR: Self-Taught ReasoningThe smallest possible self-improvement loop sits inside the rationale. A model generates a chain of thought, keeps the ones that land on correct answers, and fine-tunes on those…
- 03AlphaEvolve: Evolutionary Coding AgentsPair a frontier coding model with an evolutionary loop and a machine-checkable evaluator. Let the loop run long enough. It discovers a 4x4 complex-matrix multiplication procedur…
- 04Darwin Gödel Machine: Self-Modifying AgentsSchmidhuber's 2003 Godel Machine required a formal proof that any self-modification was beneficial before accepting it. That proof is impossible in practice. Darwin Godel Machin…
- 05AI Scientist v2: Workshop-Level ResearchSakana's AI Scientist v2 (Yamada et al., arXiv:2504.08066) runs the full research loop: hypothesis, code, experiments, figures, writeup, submission. It is the first system to ha…
- 06Automated Alignment Research (Anthropic AAR)Anthropic ran parallel teams of Claude Opus 4.6 Autonomous Alignment Researchers in independent sandboxes, coordinating via a shared forum whose logs live outside any sandbox (s…
- 07Recursive Self-Improvement: Capability vs AlignmentRecursive self-improvement (RSI) is no longer speculation. The ICLR 2026 RSI Workshop in Rio (April 23-27) framed it as an engineering problem with concrete tooling. Demis Hassa…
- 08Bounded Self-Improvement DesignsResearch has converged on four primitives for bounding a self-improvement loop. Formal invariants that must hold across every edit. Alignment anchors that cannot be modified. Mu…
- 09Autonomous Coding Agent Landscape (SWE-bench, CodeAct)SWE-bench Verified went from 4% to 80.9% in under three years. Same Claude Sonnet 4.5 scored 43.2% on SWE-agent v1 and 59.8% on Cline autonomous — the scaffolding around the mod…
- 10Claude Code Permission Modes and Auto ModeClaude Code exposes seven permission modes. "plan" asks before every action, "default" asks only for risky ones, "acceptEdits" auto-approves file writes but still confirms shell…
- 11Browser Agents and Indirect Prompt InjectionChatGPT agent (July 2025) merged Operator and deep research into one browser/terminal agent and set BrowseComp SOTA at 68.9%. OpenAI shut Operator down August 31, 2025 — consoli…
- 12Durable Execution for Long-Running AgentsProduction long-horizon agents do not run in `while True`. Every LLM call becomes an activity with checkpoint, retry, and replay. Temporal's OpenAI Agents SDK integration went G…
- 13Action Budgets, Iteration Caps, Cost GovernorsA mid-sized e-commerce agent's monthly LLM cost jumped from $1,200 to $4,800 after its team enabled the "order-tracking" skill. That is not a pricing bug. That is an agent that …
- 14Kill Switches, Circuit Breakers, Canary TokensA kill switch is a boolean held outside the agent's edit surface — a Redis key, a feature flag, a signed config — that disables the agent entirely. A circuit breaker is finer-gr…
- 15HITL: Propose-Then-CommitThe 2026 consensus on HITL is specific. It is not "the agent asks, the user clicks Approve." It is propose-then-commit: the proposed action is persisted to a durable store with …
- 16Checkpoints and RollbackEvery graph-state transition persists. When a worker crashes, its lease expires and another worker picks up at the latest checkpoint. Cloudflare Durable Objects hold state acros…
- 17Constitutional AI and Rule OverridesAnthropic's January 22, 2026 Claude Constitution runs 79 pages and is CC0. It moves from rule-based to reason-based alignment and establishes a four-tier priority hierarchy: (1)…
- 18Llama Guard and Input/Output ClassificationLlama Guard 3 (Meta, Llama-3.1-8B base, fine-tuned for content safety) classifies both LLM inputs and outputs against an MLCommons 13-hazard taxonomy across 8 languages. A 1B-IN…
- 19Anthropic Responsible Scaling Policy v3.0RSP v3.0 went into effect February 24, 2026, replacing the 2023 policy. Two-tier mitigation: what Anthropic will do unilaterally vs what is framed as an industry-wide recommenda…
- 20OpenAI Preparedness Framework and DeepMind FSFOpenAI Preparedness Framework v2 (April 2025) introduces Research Categories — Long-range Autonomy, Sandbagging, Autonomous Replication and Adaptation, Undermining Safeguards — …
- 21METR Time Horizons and External EvaluationMETR (ex-ARC Evals) is an independent 501(c)(3) since December 2023. Their Time Horizon 1.1 benchmark (January 2026) fits a logistic curve to task-success probability vs log(exp…
- 22CAIS, CAISI, and Societal-Scale RiskThe Center for AI Safety (CAIS, San Francisco, founded 2022 by Hendrycks and Zhang) publishes the four-risk framework — malicious use, AI races, organizational risks, rogue AIs …