Wildthing – A model trained on role-reversed ChatGPT conversations(youaretheassistantnow.com)

78 points by iamwil 1 year ago | 35 comments

GPT-4 Update: 32K Context Window Now for All Users(github.com)

156 points by gzer0 3 years ago | 92 comments

nanochat.karpathy.ai(nanochat.karpathy.ai)

4 points by danielfalbo 11 months ago | 0 comments

Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs(github.com)

85 points by thunderbong 1 year ago | 16 comments

ChatHN: Chat with Hacker News using OpenAI function calling(github.com)

198 points by steventey 3 years ago | 60 comments

Stelvio: Ship Python to AWS(github.com)

28 points by todsacerdoti 8 months ago | 40 comments

Turning GLM-5.3-Flash into a Jev-like decision model(privatemode.ai)

116 points by flxflx 1 month ago | 50 comments

Privatemode AI blog post describing how to prompt GLM-5.3-Flash so its first output token gives a decision in a single forward pass, benchmarked against Jev and Laya.

I built a programming language that LLMs can't use(blog.picheta.me)

244 points by dom96 8 days ago | 179 comments

Blog post by Dominik Picheta introducing KillSwitch, a programming language he designed so that large language models cannot use it.

Fine tune a 70B language model at home(answer.ai)

821 points by jph00 2 years ago | 197 comments

Answer.AI blog post announcing an open source system combining FSDP and QLoRA to train a 70B language model on two 24GB consumer GPUs.

The DuckDB Local UI(duckdb.org)

868 points by xnx 1 year ago | 181 comments

DuckDB blog post announcing a local web-based UI for DuckDB, built with MotherDuck and shipped as part of the ui extension.

A hacker's guide to language models [video](youtube.com)

749 points by rrampage 3 years ago | 35 comments

YouTube video by Jeremy Howard titled "A Hackers' Guide to Language Models," a code-first introduction to using and understanding LLMs.

Training LLMs from ground zero as a startup(yitay.net)

360 points by swyx 2 years ago | 92 comments

Yi Tay's blog post on the experience of training large language models from scratch at a startup (Reka), covering compute, infrastructure, and lessons learned.