Alphabell.

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
AlphaEvolve
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

17 Nov 2026Full radar →

11 picked from 47 candidates · 30 sources read · 77 loops indexed

  1. 01
    Loop of the dayPaperarXiv16 Nov 2026AI R&D evals

    WeightBench: Evaluating Language Models as Weight-Space Programmers

    The loop: Frontier agents are evaluated on their ability to read, fix, and write the weights of other neural networks. This benchmark guides the development of agents that can directly program model weights, improving future models.

    Weight-space programming is a fascinating frontier where models directly edit the parameters of other networks, bypassing gradient descent entirely.

    loop fit 9/10Cosimo Galeone, Anna Ettorre, Ginevra Mariani, Minsu Park, Giuseppe Ettorre,...via arXiv
    WeightBench: Evaluating Language Models as Weight-Space Programmers
  2. 02
    PaperarXiv14 Nov 2026Kernels and compilers

    CompoundingKernel: Self-Improving from Zero to First

    The loop: CompoundingKernel agents search for and write optimized GPU kernels. These kernels improve the execution speed of the hardware running the agents, making the search process more efficient.

    loop fit 9/10Qian Qu, Hongyang Wang et al.via Hugging Face Papers
    CompoundingKernel: Self-Improving from Zero to First
  3. 03
    Blog postMETR16 Nov 2026AI R&D evals

    Measuring alignment eval tells

    The loop: Investigator agents probe and identify tells in alignment evals, which improves the robustness of the evaluation suite, which makes the training of future models more reliable.

    loop fit 8/10via METR
    Measuring alignment eval tells
  4. 04
    PaperarXiv12 Nov 2026Tools and harness

    Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent

    The loop: An optimization loop reads agent failure traces and makes targeted changes to the agent's instructions. These changes improve the agent's performance and reduce its operating costs.

    loop fit 9/10Wenhong Zhu, Xuefeng Li et al.via Hugging Face Papers
    Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent
  5. 05
    PaperarXiv16 Nov 2026Self-reward and self-play

    Benchmarks Don't Talk Back: Learning Through Self-Disagreement

    The loop: A language model generates its own antithesis to a position and rules on whether the case stands. It then trains on that ruling to improve its dialectical competence.

    loop fit 9/10Aayush Marasini, Barsat Khadka, Nick Rahimivia arXiv
    Benchmarks Don't Talk Back: Learning Through Self-Disagreement
  6. 06
    PaperarXiv12 Nov 2026AI R&D evals

    Measuring alignment eval tells

    The loop: Investigator agents probe environments to identify tells that distinguish alignment evals from capabilities evals. This improves the robustness of the evaluation suite, making the training of future models more reliable.

    loop fit 8/10Soheil Abbasloo, Peng Chengvia arXiv
    Measuring alignment eval tells
  7. 07
    PaperarXiv13 Nov 2026Hardware and chips

    Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study

    The loop: AI agents design industrial-level chip floorplans. This improves the hardware that the agents or their successors run on, making them faster and more capable.

    loop fit 8/10Simon Tang, Wenjie Shi et al.via arXiv
    Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study
  8. 08
    PaperarXiv16 Nov 2026Kernels and compilers

    Last year we built megakernels. This year we deleted them: The road to Together Compiler

    The loop: AI agents rewrite and fuse GPU kernels in a model's forward pass. This improves the inference speed of the models the agents serve, making them faster.

    loop fit 7/10Sergio Hern\'andez-Guti\'errez, Matteo Merler, Ilze Amanda Auzina, Joschka...via arXiv
    Last year we built megakernels. This year we deleted them: The road to Together Compiler
AlphaEvolve
ProjectGoogle DeepMind
AlphaEvolve
  1. Gemini models propose code changes
  2. Evaluators keep best scoring versions
  3. Finds better Gemini training kernels
  4. Lowers cost to train next Gemini models
  5. repeat
Kernels and compilersGoogle DeepMind · 2025
Darwin Gödel Machine
PaperarXiv
Darwin Gödel Machine
  1. Coding agent edits its own code
  2. Scored child agents enter the archive
  3. Archived agents make later self modifications
  4. repeat
Self-modifying agentsUBC, Vector Institute, Sakana AI · 2025
AlphaChip
ProjectGoogle DeepMind
AlphaChip
  1. RL agent lays out TPU blocks
  2. Better layouts make AI hardware cheaper
  3. Agent pre-trains on earlier chip generations
  4. repeat
Hardware and chipsGoogle DeepMind, Google Research · 2020
autoresearch
Mini-projectGitHub
autoresearch
  1. Coding agent edits LLM training script
  2. Runs a 5-minute training job
  3. Keeps change if validation improves
  4. Changes transferred to larger models
  5. repeat
Research automationAndrej Karpathy · 2026
ScholarEvolve
PaperarXiv
ScholarEvolve
  1. Research agent writes harness mutation blueprints
  2. Coding agent implements harness module changes
  3. Winning harness becomes the new champion
  4. New champion harness runs further generations
  5. repeat
Tools and harnessYang et al. (UC Santa Barbara, Microsoft) · 2026
Nemotron-4 340B
PaperarXiv
Nemotron-4 340B
  1. Aligned model generates training data
  2. Reward model judges and filters it
  3. Data trains next intermediate instruct model
  4. Next model generates better alignment data
  5. repeat
Training dataNVIDIA · 2024
Self-Rewarding LMs
PaperarXiv
Self-Rewarding LMs
  1. Model generates candidate responses to prompts
  2. Model scores them itself as a judge
  3. Scores become preference pairs for DPO
  4. Trained model becomes next generator and judge
  5. repeat
Self-reward and self-playMeta, NYU (Yuan et al.) · 2024
Claude Code
ProjectAnthropic
Claude Code
  1. Claude Code writes its own code changes
  2. Changes become next Claude Code versions
  3. Release becomes harness for next development round
  4. repeat
Self-modifying agentsAnthropic · 2025
KernelEvolve
ProjectarXiv
KernelEvolve
  1. LLM agents write and benchmark kernels
  2. Kernels speed up AI model training
  3. Session data post-trains smaller kernel models
  4. repeat
Kernels and compilersMeta · 2025
PostTrainBench
BenchmarkarXiv
PostTrainBench
  1. Coding agent writes fine-tuning code
  2. Agent post-trains a base LLM
  3. Trained model scored on target benchmark
  4. One turn of model training another
  5. repeat
AI R&D evalsELLIS Institute Tubingen, MPI-IS, University of Tubingen, Thoughtful Lab (Rank et al.) · 2026
Self-training learned optimizers
FoundationarXiv
Self-training learned optimizers
  1. Learned optimizers update other learned optimizers
  2. Training keeps best performing optimizer parameters
  3. Better optimizers train each other faster
  4. repeat
Architecture and optimizer searchMetz et al. (Google Research, Brain Team) · 2021
CoT monitoring
PaperarXiv
CoT monitoring
  1. LLM reads reasoning model thoughts
  2. LLM flags reward hacking behavior
  3. Signal feeds back into training reward
  4. Trains more aligned capable agents
  5. repeat
Interpretability and oversightOpenAI (Baker et al.) · 2025

Support for loop research

How to apply →

Have a loop worth building?

Tell us what the AI improves and how the improvement comes back. Applications for grants, fellowships and compute all start on the contact page.

Get in touch