Three GPTs that play chess at ~1,900 Elo with no search; same games, different tokenizers - wezn/chess-gpt ...
Attack your own SQL-write guardrail. Naive vs hardened detector on a labelled corpus. - sghatge/safe-to-send-07-red-team-your-guardrail ...
An autonomous, multilingual emergency response system built for India's 108 Emergency Medical Services, powered by Sarvam AI.
Ordinary progressive delivery answers: is the new service responding? Production ML also needs to answer: is the new decision function safe, and do we have enough evidence to know? That second ...
Agent skills for Claude Code and Codex: plain writing, papers and rebuttals, Codex orchestration - ddofer/DSkills ...
A ready-to-use starting point for doing computational research on the lab's multi-omics knowledge graph — without writing database queries or analysis code yourself. The knowledge graph is the lab's ...
Daily App Store chart movers brief: biggest gainers, losers, new entrants and new releases per storefront, with estimate ranges, cross-country moves and streaks. Node CLI + browser page on the ...
Git pre-commit hook that blocks commits containing secrets (API keys, tokens, private keys) using pattern matching and entropy analysis. - unknown6889/secret-leak-prevention ...
Identifies 37 cat and dog breeds by fine-tuning a pretrained ResNet-50 on Oxford-IIIT Pet: 93.6% test accuracy, with tests and a Gradio demo - Gauhet/pet-breed-classifier ...
A collection of projects completed during the 42 Piscine - loresaba/42-piscine ...
Robots often repeat tasks in the same or slowly changing environment. A successful execution therefore offers useful evidence about which behaviors work under local conditions. Retrieve-then-Steer ...
A local chess workspace: five engines, a coach that grades every move, and a resource governor that never lets chess pin your laptop. - Ekka-Barber/Chess-Play-Fun ...