Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,235
repos tracked
175
surfaced this week
194
created < 30d
Python
top language
15 repos
-
Manipulating RLHF corpus to reduce sycophancy outcomes
-
Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.
-
List of papers on hallucination detection in LLMs.
-
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
-
Translate between English and Claudish with tiny ProgramAsWeights functions.
-
Language model tokenization at GB/s
-
DELPH-IN Documentation
-
[EMNLP 2026] A counterfactual chart generation pipeline for evaluating chart reasoning in vision-language models.
-
[ICML'26] "Agent Learning via Early Experience" (Open-source reproduction)
-
Efficient few-shot learning with Sentence Transformers
-
Tongyi Deep Research, the Leading Open-source Deep Research Agent
-
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.