Benchmark: can an LLM make a language model better at math by editing its weights directly? (Qwen3.5-0.8B, MATH-500/GSM8K, via OpenRouter)
-
Updated
Nov 3, 2026 - Python
Benchmark: can an LLM make a language model better at math by editing its weights directly? (Qwen3.5-0.8B, MATH-500/GSM8K, via OpenRouter)
Agent skill for weight-space programming: edit LLM weights
Open-source weight space editing for small language models. Direct tensor edits, measured hill climbs and a Hugging Face workbench.
Give AI agents tools to inspect, edit, and test model weights: an MCP harness and Python toolkit for weight-editing experiments.
SGNE-CC: training-free 3.13 MiB norm-preserving weight edit for Qwen3.5-0.8B vs. MIT-p50c across 5 benchmarks at 32k tokens (38 JSONL traces & CPU verifier)
Claude agents repair a thinking loop in Qwen3.5-0.8B by editing its weights directly (rank-1 edits, no training). Pre-paper, code, lab notebook and data.
Model engineering: AI agents edit a model's internals in small, signed, reversible diffs. Research programme.
Weight-space programming on a 27B production model: sandboxed kernel, metered forward passes, sealed held-out eval, every transcript
Make your own small AI that runs on a laptop: teach it your documents or describe how it should answer. Honest report cards, fixes by editing weights, one-file export for Ollama.
Direct weight surgery for LLMs — edit weights, not gradients. Extract the arrow, leave the body intact.
Fixing small language model defects (reasoning loops…) by having an LLM (Claude Opus in Claude Code) edit their weights directly, without training — measured against the original by slm-quality-bench
Signet: fixing a language model by editing its weights with plus-or-minus steps only. Qwen2.5-0.5B, full sealed-test record.
Calmer Qwen3.8 Flash Next: fixed 44+45 weight edits, production-runtime comparisons, layer analysis, and all successful, failed, and interrupted experiment records.
Closed-form weight edits for Gemma 4 that a coding agent can drive: find where the model makes a choice, build low-rank edits without gradients, and judge each against size-matched random edits (target, keep, side effects). MLX and PyTorch backends; exports LoRA adapters.
Can frontier models fix a coding agent by editing its weights? Code, protocols, records, frozen gate reports and agent configs of the Gemma 4 E4B weight-edit study, with the full paper (PDF) and both Kaggle writeups.
WeightX: Open-source Weight-Space Programming (WSP) harness in Rust & Tauri 2 + PyTorch sidecar for safe, declarative and verified LLM weight surgery.
Can an LLM repair sycophancy by editing weights directly? A gradient-free edit of 0.23 % of Qwen2.5-0.5B cuts wrong-hint flips from 76.8 % to 32.3 % on a blind test split, but correct hints also help less on unknown questions.
The map of modifying model weights directly: knowledge editing, steering & abliteration, task arithmetic, unlearning, and the weight-space programming wave. 权重编辑全景 · 中英双语 · Daily radar 🤖
To associate your repository with the weight-editing topic, visit your repo's landing page and select "manage topics."