platform.openai.com/docs/gui… Optimizing LLMs for accuracy is hard - despite opening our talk at DevDay in November last year with those same words, achieving the right level of accuracy for production remains a challenge. I’ve tried to collect my learnings from the last year into our latest guide, Optimizing LLMs for Accuracy. The key sticking points are consistently: - Knowing how to start optimizing accuracy - When to use what optimization method - What level of accuracy is good enough for production This paper gives a mental model for dealing with all of these. Hope you enjoy, and please comment with any additional content you’d like to see - we’d love to share more of our learnings where they can help you.

I think there's maybe really something here, look at this. I got GPT to respond to the prompt from this uml.edu/docs/sample-essay_tc…. Then I got a sequence of embeddings for each word in both the human- and GPT- authored essays. You can see how the human one moves around more.

What the refs think is happening beneath the ball that's clearly on the ground #SCOvFRA

Parcel delivery firm DPD have replaced their customer service chat with an AI robot thing. It’s utterly useless at answering any queries, and when asked, it happily produced a poem about how terrible they are as a company. It also swore at me. 😂

For every 10 likes this gets, I will ask ChatGPT to make this goose a little sillier.

The iconic Sycamore Gap tree on Hadrian's Wall Path in Northumberland has been felled overnight. We're waiting more information on this. Pics - Amanda Marks, Author, Facebook.

Does a language model trained on “A is B” generalize to “B is A”? E.g. When trained only on “George Washington was the first US president”, can models automatically answer “Who was the first US president?” Our new paper shows they cannot!

No More GIL! the Python team has officially accepted the proposal. Congrats @colesbury on his multi-year brilliant effort to remove the GIL, and a heartfelt thanks to the Python Steering Council and Core team for a thoughtful plan to make this a reality. discuss.python.org/t/a-steer…

Pleased to have @a16zcrypto lead our $43M Series A and join us on the @gensynai journey! Thanks also to @coinfund, @edenblockvc, @ZeePrimeCap, @Maven11Capital, @JSquare_co, @id4vc, Peer, @ai, @protocollabs, @M31Capital, and some fantastic angels theblock.co/post/234092/bloc…

Really awesome to see tripnotes.ai featured in the upcoming @MicrosoftStore !!

Not long ago, breakthroughs in AI research often came from lone academics or small teams using desktop hardware. These days, not so much. Are you anxious about how to stay competitive in AI as an academic? @yannakakis and I wrote this piece for you: arxiv.org/abs/2304.06035

Say goodbye to travel plans. This AI app creates entire itineraries with recommendations for your next trip. The best part- it's completely free 👇

Spoiler: it's going to be a 20-lines Python script that calls model.fіt() github.com/twitter/the-algor…

Tripnotes made over 40,000 itineraries and recommendations on its first day! Thank you for the support and feedback. 🙏

Meet Tripnotes, a travel A.I. with taste. Ask it for recommendations, itineraries, and more. Head to tripnotes.ai to give it a spin!

If you’re cross about being compared to Nazis, then calling for your critics to be silenced & sacked probably isn’t the best way to prove them wrong.

Using AI to generate travel plans is 🤌, but using plans when you arrive at your destination needs to be simple & seamless. Enter iOS 16 and Live Activities. Now you can explore freely without the stress of missing a place or reservation.