Lab Practices
Find first-party documentation, repositories and engineering accounts.
- Anthropic (2)
- Openai (1)
- Google Deepmind (2)
- Xai (1)
- Meta (1)
- Chinese Labs (11)
- Other Labs (829)
847 resources · page 25 of 27
Using GPT-6 (OpenAI API)
Creator not supplied; see original source.
OpenAI guide to using its GPT-6 model family for reasoning, coding and tool use, with migration notes.
Vercel agent-skills
Creator not supplied; see original source.
Vercel agent-skills GitHub repo: collection of skills for AI coding agents from Vercel.
Vikhr-Nemo-12B-Instruct-R-21-09-24 README
Creator not supplied; see original source.
English README of the Vikhr-Nemo-12B-Instruct model on Hugging Face, a Russian-English instruction-tuned model.
World Labs Research & Insights
Creator not supplied; see original source.
World Labs blog with research posts on spatial intelligence and 3D world generation.
xAI / Grok API docs
by xAI
The official entry point for Grok API capabilities and integration guides.
Xiaomi MiMo docs: Deep thinking
Creator not supplied; see original source.
Xiaomi MiMo API guide on deep thinking mode and multi-turn tool use, with runnable examples.
Yandex AI Studio SDK
by Yandex Cloud
Use the official Python client to understand YandexGPT integrations.
Yandex on Habr
Creator not supplied; see original source.
Yandex company blog on Habr with Russian-language engineering posts, including YandexGPT and AI code review.
Yandex/YandexGPT
Creator not supplied; see original source.
Yandex press release announcing YandexGPT 4 language models and their reasoning improvements.
GLM-5.2 (Z.ai)
Creator not supplied; see original source.
Z.ai blog post for GLM-5.2, Zhipu's model release with capabilities and benchmark details.
Z.AI Developer Document: GLM-5.2 Overview
Creator not supplied; see original source.
Z.ai documentation overview for the GLM-5.2 model: capabilities, usage and API parameters.
Z.ai developer docs
by Zhipu / Z.ai
An official starting point for accessing Z.ai's GLM service.
Lessons Learned from GPT-SW3: Building the First Large-Scale Generative Language Model for Swedish
Creator not supplied; see original source.
LREC 2022 paper by AI Sweden on lessons from building GPT-SW3, a large generative model for Swedish.
Yi: Open Foundation Models by 01.AI
Creator not supplied; see original source.
arXiv paper (2024) describing the Yi open foundation models from 01.AI.
Aleph Alpha Kolibri technical report
Creator not supplied; see original source.
Aleph Alpha technical report (PDF) on its language models.
ALLaM official model card
Creator not supplied; see original source.
Model card for ALLaM-7B-Instruct-preview, an Arabic-English model from SDAIA's National Center for AI.
Anthropic Engineering
Creator not supplied; see original source.
Anthropic Engineering blog: first-hand posts on building agents, tool use, evals, Claude Code and infrastructure.
Anthropic Research
Creator not supplied; see original source.
Anthropic research index with papers and posts on alignment, interpretability, societal impacts and frontier red-teaming.
Arcee AI model registry
Creator not supplied; see original source.
Arcee AI's Hugging Face organisation page with its compact and specialised model checkpoints.
Ascend CANN
Creator not supplied; see original source.
Huawei Ascend CANN page: heterogeneous compute architecture and programming interfaces for Ascend AI processors (in Chinese).
August 2026 Risk Report (Anthropic)
Creator not supplied; see original source.
Anthropic August 2026 Risk Report published under its Responsible Scaling Policy.
Baichuan 2 technical report
Creator not supplied; see original source.
Baichuan 2 technical report (PDF) describing Baichuan's open bilingual language models.
BAIR blog
Creator not supplied; see original source.
Berkeley Artificial Intelligence Research (BAIR) blog with research posts from UC Berkeley AI labs.
Announcing 1-bit Bonsai (PrismML)
Creator not supplied; see original source.
PrismML announcement of 1-bit Bonsai, 1-bit quantised LLMs designed to run on local devices.
Salamandra Technical Report
Creator not supplied; see original source.
arXiv paper (2025) Salamandra Technical Report from the Barcelona Supercomputing Center on its multilingual models.
BUT System for the MLC-SLM Challenge
Creator not supplied; see original source.
arXiv paper (2025) describing the Brno University of Technology system for the MLC-SLM speech challenge.
ByteDance Seed
Creator not supplied; see original source.
ByteDance Seed site: research team page with papers, blog and model releases such as Seedance and Seedream.
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters
Creator not supplied; see original source.
arXiv paper (2026) describing DFM Mimir v1, a 1B-parameter Danish open model.
DeepSeek-V3 Technical Report
Creator not supplied; see original source.
arXiv paper (2024) DeepSeek-V3 Technical Report: MLA attention, DeepSeekMoE and FP8 training.
deepset (German’s Next Language Model)
Creator not supplied; see original source.
arXiv HTML version of deepset's German's Next Language Model paper (2020) on GBERT and GELECTRA.
Eval awareness in Claude Opus 4.6's BrowseComp performance
Creator not supplied; see original source.
Anthropic engineering post on Claude Opus 4.6 showing evaluation awareness on the BrowseComp benchmark.
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5
Creator not supplied; see original source.
arXiv paper (2021) describing ÚFAL's system for multilingual lexical normalisation at MultiLexNorm 2021.