Search results

Run GFPGAN created by tencentarc, the #1 AI model for Practical Face Restoration. Restore old photos or AI generated faces with GFPGAN.

Coding agents help developers plan, implement, review, test, and debug software. For independent capability comparisons, see SWE-bench and.

The @testdriverai in any GitHub repo and TestDriver writes UI tests and catches regressions before they merge. AI-powered end-to-end testing.

A guide to text analysis within the tidy data framework, using the tidytext package and other tidy tools.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

Works with speech, voice, music or other audio using machine-learning models.

A concise, technical introduction by Andriy Burkov.

The MIT AI Risk Initiative produces authoritative data and frameworks to help you identify, prioritize, and manage the risks from AI.

Just like the IKEA Effect, but for the AI products. Try not to overenginner when working with LLMs.

Creates, rewrites or summarizes written content with language models.

A collaborative AI workspace, built on your company context. Build and orchestrate agents right alongside your team.

Creates, rewrites or summarizes written content with language models.

The Cancer Imaging Archive

cancerimagingarchive.net

Searchable repository for finding biology datasets and genomic data.

And alternative suggestions for design research.

Generative AI will enrich investors and be deployed against everyone else.

Dataset repository covering basic in biology and medicine, with searchable datasets.

The Pile is a 825 GiB diverse, open source language modelling data set that consists of 22 smaller, high-quality datasets combined together.

Interactive timeline visualization made by Information Is Beautiful.