Tutorials & how-to

AICognition describes autonomous testing in Devin, where the agent writes a source-grounded test plan, operates the app through computer use, and returns labeled screenshots and an annotated video.

Why it matters: The post explains how computer use, test plans, deterministic login scripts, and annotated recordings let Devin verify its own code changes end to end.

AIMiniMax says its M2 series could not output the name Ma Jiaqi, a failure it traced to post-training data that rarely included the token.

Why it matters: The post traces a community-noticed token failure through tokenizer, embedding, and lm_head tests, showing how post-training data coverage can cause low-frequency token drift.

AICognition reports that multi-agent setups work best when writes stay single-threaded and extra agents contribute intelligence instead of actions.

Why it matters: The post gives concrete findings on which multi-agent setups work, including clean-context code review and smart-friend escalation, and where they still fail.

AIAnthropic describes Claude Code auto mode, which delegates approval of agent actions to model-based classifiers instead of manual prompts or skipped permissions.

Why it matters: The post explains the layered classifier design and its measured tradeoffs, showing how autonomous coding agents can cut approval fatigue without fully removing risk.

AIAnthropic's Labs team describes a three-agent harness with planner, generator, and evaluator agents for building full-stack applications over multi-hour autonomous coding sessions.

Why it matters: The post shows how a generator-evaluator loop, with explicit grading criteria and a tuned QA agent, turned a solo run's broken output into a working app, and how the harness was pruned as models improved.

AINano Banana 2, also called Gemini 3.1 Flash Image, adds visual grounding with Google Search, 512px resolutions, and extreme aspect ratios of 1:8 and 1:4.

Why it matters: The guide compares Nano Banana 1, 2, and Pro with concrete routing advice, which helps developers decide which model to default to and how to control cost.

AICognition reports merging 659 Devin PRs into its own codebase last week, up from 154 in its best week in 2025.

Why it matters: The post shows concrete workflows for using Devin across Slack, Linear, and code review, with specific usage figures that help teams judge fit for their own engineering processes.

AINicholas Carlini of Anthropic's Safeguards team describes an agent-team setup where 16 Claude instances worked in parallel on a shared codebase without human intervention to write a Rust-based C compiler.

Why it matters: The post shows concrete harness design choices for long-running agent teams, including test design, locking, and parallel work division, that readers can adapt to their own autonomous projects.

AIAnthropic's performance engineering lead Tristan Hume describes how a take-home test for hiring performance engineers was repeatedly defeated by successive Claude models.

Why it matters: The post traces how each Claude model defeated the take-home test, showing concrete redesign tradeoffs for evaluating engineers when AI assistance is available.

AIThinking Machines Lab describes on-policy distillation, which samples rollouts from a student model and has a teacher grade each token with reverse KL. The authors report that this matches Qwen3-style reasoning results at a fraction of RL's cost, with AIME'24 reaching 70% in about 150 steps from a 400k SFT checkpoint.

Why it matters: The post explains why on-policy distillation gives dense per-token feedback, letting a small model match RL results at much lower compute cost.

AICognition rebuilt its Devin coding agent for Claude Sonnet 4.5, reporting 2x faster performance and 12% better results on its Junior Developer Evals, now available in Agent Preview.

Why it matters: The post explains which agent behaviors changed under Sonnet 4.5, such as context-window awareness and note-taking, that forced a rebuild rather than a simple model swap.