Software maintenance is changing. A few months ago, I had to tell Codex exactly where to look for dead code. Now it can find candidates in Slack, check them against production telemetry, and draft cleanup PRs. Here’s how we do this at OpenAI. https://developers.openai.com/blog/maintaining-software-with-the-gpt-6-family

Four Gemini 4 Argon agents, one shared Minecraft world, one goal: defeat the Ender Dragon. 27 hours and 2,783 self-written programs later, the dragon fell. https://x.com/i/article/2111007444981645312

Beam is now available across platforms, with open weights under the Apache 2.0 license - in collaboration with an ecosystem of 40+ partners. We're releasing: - Weights, tokenizer, and reference implementation - BF16, FP8 and NVFP4 weights and a DFlash2 drafter - The open source harness we built and trained Beam on: Mirror CLI Weights and model card on Hugging Face: https://huggingface.co/reflection

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery Blog: https://pub.sakana.ai/agentic-scientist/ GitHub: https://github.com/SakanaAI/AI-Scientist-v3 arXiv: https://arxiv.org/abs/2610.18933 Since 2024, we’ve used The AI Scientist as a way to test how far AI alone can take scientific research, from v1 to v2 to the paper published in Nature earlier this year. The Agentic Scientist is the next step in that line of work, built for the era of coding agents. Coding agents such as Codex and Claude Code now carry out long software tasks on their own. Handing them a research problem, however, tends to produce a strong hyperparameter optimizer rather than a scientist: scores go up, but ideas stay narrow, and the reasons for the gain are rarely examined. The Agentic Scientist makes the research loop explicit. It wraps off-the-shelf coding agents in a scaffold that controls what they see, what they write, how they are evaluated, and how results are handed to the next stage. Parallel workers test hypotheses against rubrics defined before any experiment runs, share successes and failures through a common memory, and then ablate the winning program to generate evidence. We used an early version of the system to study Error Diffusion, a biologically motivated alternative to backpropagation. Our researchers set the question and the rubric, chose directions at each stage, and verified the results, references, and claims before submission. The resulting paper was accepted as an oral presentation at ALIFE 2026. In autonomous runs, the system also raised Doc-to-LoRA retrieval accuracy from 52% to 98% on multi-needle tasks and designed a learned evolution strategy that improves over its CMA-ES reference on unseen tasks. Alongside it we release AutoIllustrate, a pipeline for scientific figures that keeps an editable http://draw.io file as the source of truth, so every diagram can be corrected by hand. Humans define the question and the standards of evidence; agents expand the experiments researchers can run. We call this Co-Discovery, and we are releasing both systems as open source for the community to build on.