AI makes AI better.

A daily hub for work where AI is part of the loop that improves AI, each entry with its loop spelled out. Read more →

1/4

A loop in motion

Project · Google DeepMind

Gemini models propose code changes

From the labalphaBell Qwen Open27B post-training research, with capability tradeoffs measured.Explore the model → From the labModel ObservatoryMeasured Flint and Qwen traces with published decoder maps.Open the lab tool → From the labMiniMax Video BudgetVisualize sampled frames, two-frame groups and vision placeholders.Try the inspector → From the labMOSS Blind Layout CheckCompare exact text and placement in two local images.Try the blind check → From the labAgent Request Evidence LadderSee what a trace proves about an agent's request and its outcome.Explore the cases →

Today's radar

11 Nov 2026Full radar →

7 picked from 136 candidates · 31 sources read · 76 loops indexed

01
Loop of the dayPaperarXiv11 Nov 2026Training data
One Byte, One Token: Byteifying a 27B Hybrid-Attention LLM with Self-Generated Data
The loop: A 27B subword model generates on-policy dialogue and behavioral supervision data, which is used to train its conversion into a pure byte-level model, making its successor capable of byte-level processing.
A 27B model generates its own training data to convert itself into a pure byte-level model, demonstrating how models can bootstrap their own architectural transformations.
loop fit 9/10Liwei Zhang, ZhiMing Tongvia arXiv
02
PaperarXiv7 Nov 2026Training data
No Second Run: Does RSI Stop at Frontier Pre-training?
The loop: The system decomposes frontier pre-training into smaller loops that repair broken steps, which improves the data pipelines and infrastructure, making the resulting foundation model better.
loop fit 9/10Xiaojie Cai, Jiayi Chen et al.via arXiv
03
ProjectGitHub8 Nov 2026Tools and harness
TokenRhythm/InfraRSI
The loop: The InfraRSI agentic harness co-optimizes launch knobs and code patches for distributed training, which improves the training infrastructure, making the system more efficient at running its own optimization tasks.
loop fit 8/10TokenRhythmvia GitHub
04
Blog postAnthropic7 Nov 2026Training data
Diluting Poisoned Fine-Tuning Data Can Strengthen Its Effect
The loop: A model analyzes the effects of poisoned fine-tuning data, which improves data filtering strategies, which makes future models more robust against data poisoning.
loop fit 8/10via Anthropic Alignment
05
PaperarXiv10 Nov 2026Self-modifying agents
When Should Agents Remember? Falsification-Gated Self-Evolution for LLM Agents
The loop: An LLM agent generates structured hypotheses from its experiences and tests them through a falsification-gated process, which improves its persistent memory, making the agent more successful and safer at future tasks.
loop fit 9/10Runxuan Tang, Haoyu Gao et al.via arXiv
06
ProjectGitHub5 Nov 2026Research automation
zou-group/BVSR
The loop: The BVSR framework applies evolutionary principles to the generation and selection of creative research ideas, which improves the AI scientists, making them better at autonomous scientific discovery.
loop fit 7/10zou-groupvia GitHub
07
PaperarXiv11 Nov 2026Tools and harness
Compile-Gated Lean Proof Refactoring with Enterprise Agent Practices: A Model per Step under a US$3 Cap, Followed by Programmatic Rewrite Rules
The loop: Vexorium-Agent records its proof attempts and converts learned patterns into compiler-checked programmatic rewrite rules, which improves its own harness, making the agent more effective at solving future Lean proofs.
loop fit 9/10Bobber Chengvia arXiv
08
PaperarXiv9 Nov 2026Research automation
Where is all the AI safety research uplift?
The loop: Frontier AI models perform research and engineering tasks to accelerate capability progress. This increased development velocity directly speeds up the creation of successor models, which are in turn more capable at research and engineering.
loop fit 9/10Yifan Zhang, Hengxuan Lou, Xinkui Zhao, Rengrong Xiong, Naibo Wang, Chang Liu,...via arXiv