Machines

I’m one of the first employees in Taranis, and I’ve been in the company for 8 years. I remember the day we grew to more than one team, and we finally decided to have some internal documentation…

Explores regions where models fail but humans succeed. Based on https://arxiv.org/abs/2402.00793. - GitHub - sunildkumar/model_indistinguishability: Explores regions where models fail but humans s...

You can fine-tune Copilot code completion by creating a custom model based on code in your organization's repositories.

End of year reflections on how people are using genAI at work

Don't worry, this half-baked Python script is for educational purposes onl-hahaha

Normcore LLM Reads · GitHub

Exploring how patterns and experiences will change in a world driven by Artificial Intelligence

Here’s how I’m blocking “artificial intelligence” bots, crawlers, and scrapers.

Tips to maximize coding flow and minimize distractions when working with coding copilots

Essay Competition Winner

Why this is the first rule, some baseline heuristics, and when to move on to machine learning.

Nature - Hallucinations (confabulations) in large language model systems can be tackled by measuring uncertainty about the meanings of generated responses rather than the text itself to improve...

When I first started learning about artificial intelligence, it had absolutely nothing to do with large language models.

Follow these strategies to improve your Copilot results.

In this prompt guide for GitHub Copilot, two GitHub developer advocates, Rizel and Michelle, will share examples and best practices for communicating your desired results to the AI pair programmer.

AGI by 2027 is strikingly plausible. GPT-2 to GPT-4 took us from ~preschooler to ~smart high-schooler abilities in 4 years. Tracing trendlines in compute (~0.5 orders of magnitude or OOMs/year), algorithmic efficiencies (~0.5 OOMs/year), and “unhobbling” gains (from chatbot to agent), we should expect another preschooler-to-high-schooler-sized qualitative jump by 2027. Look. The models, they just

Why LoRA Is Essential For Model Fine-Tuning

A few weeks ago, I had the pleasure of attending FQXi’s Setting Time Aright conference, part of which took place on a cruise from Bergen, Norway to Copenhagen, Denmark.  (Why aren’…

Musings of a Computer Scientist.

Experiences of using ChatGPT on a range of technical writing

At work we recently started experimenting with generative AI for assistance with programming. We have a new Visual Studio Code plugin which we can ask questions in English, and it spits back code. It was a really interesting piece of, well, mandatory training. I've formed some op...

Also, my book has a cover (also I have a book coming out)

Don't overcomplicate things

Building an implementation of garbled circuits from the ground up

Open-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.

A conversation with Imran Chaudhri, a former Apple designer and co-founder of Humane about the future of personal computing in the age of artificial intelligence.

The latest meta for using ChatGPT as the service has evolved and grown since its release nearly a year ago

Many are worried about AI taking inspiration from their ideas. It couldn't be more misguided. The internet is a copy-paste machine - being copied is the goal...