Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
☆1,004Oct 29, 2026Updated last week
Alternatives and similar repositories for lm_understand-logs
Users that are interested in lm_understand-logs are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆98Updated this week
- DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses☆146Oct 30, 2026Updated last week
- Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, P…☆24Updated this week
- Official code for the ICML 2026 paper "Modular Pretraining Enables Access Control" (GRAM).☆44Jul 8, 2026Updated 3 months ago
- A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.☆671Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A catalog of every MLP neuron and attention head of Qwen3-8B and Gemma 4 12B, read from the weights through two Jacobian lenses (R and S)…☆41Updated this week
- ☆16Oct 8, 2026Updated 3 weeks ago
- Cross-provider market data validation for OHLCV prices, adjusted returns, discrepancies, and consensus datasets.☆16Sep 28, 2026Updated last month
- Qwen3.5-2B with a SIMT GPU inside its weights, 45 compiled layers in front of Qwen’s own, using its Gated DeltaNet layers as registers an…☆117Updated this week
- ☆478Oct 18, 2026Updated 2 weeks ago
- AI coding agent that makes a small model beat a frontier one☆367Updated this week
- [ICML'26] Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning☆17Jun 1, 2026Updated 5 months ago
- Run unmodified FreeCAD with a Siemens NX-style UI/UX: ribbon, NX mouse and keyboard shortcuts, NX workflow. No fork, separate profile. No…☆15Updated this week
- Towards a More Autonomous Agent System☆19,341Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆11Jul 20, 2026Updated 3 months ago
- IP forge - discover, fetch and install open PDK IP packages☆12Aug 6, 2026Updated 3 months ago
- 🧂[Preprint] Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation☆25Oct 2, 2026Updated last month
- ☆21Mar 6, 2026Updated 8 months ago
- MCP server for Lacuna, a research map for machine learning: search directions, papers, authors, venues, and AI-generated research proposa…☆56Updated this week
- Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention☆396Updated this week
- Reproducible encoder downstream fine-tune eval harness☆11Jul 27, 2026Updated 3 months ago
- Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generat…☆7,305Updated this week
- Official code for the paper "Rendering String Diagrams Recursively".☆14Aug 13, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Pretraining Transformers Without Backpropagation☆305Oct 6, 2026Updated 3 weeks ago
- ISO: Isospectral Optimization for RLVR☆33Aug 11, 2026Updated 2 months ago
- eplicates and extends Anthropic's April 2026 paper ["Emotion Concepts and their Function in a Large Language Model"](https://transformer-…☆35Apr 7, 2026Updated 6 months ago
- reproducing the flapping airplanes megakernel, in collab with magni☆129Updated this week
- Repository for "User awareness in frontier models: who's asking shifts what models say"☆16Aug 6, 2026Updated 3 months ago
- Qwen3.5-2B with a filesystem compiled and inserted directly into its weights.☆90Updated this week
- Compile neural networks into DOOM maps, where voodoo dolls do the arithmetic☆59Updated this week
- ORA: Open Robot-Use Agents☆110Oct 21, 2026Updated 2 weeks ago
- Hessian Null Space Continuation (HNC): traversing the solution space of neural networks☆12Sep 30, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Visualize Claude Code session trajectories — time, tokens, tools, and thinking — as an interactive Gradio app.☆21Sep 3, 2026Updated 2 months ago
- Survey: The Path to Recursive Self-Improving Agents: Foundation, Framework, and Future Directions☆61Oct 22, 2026Updated 2 weeks ago
- A measurement-first lab for low-latency local camera inference with Glance.☆53Sep 24, 2026Updated last month
- ☆29Updated this week
- evals.typesafe.ai workflow code published☆21Sep 29, 2026Updated last month
- Code for the paper “The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions”☆307Updated this week
- Code for After42, coming soon.☆27Oct 27, 2026Updated last week