Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)
Use cases, techniques, alignment, finetuning, and critiques against LLM-evaluators.
AI/ML
What’s Really Going On in Machine Learning? Some Minimal Models
Stephen Wolfram explores minimal models and their visualizations, aiming to explain the underneath functionality of neural nets and ultimately machine learning.
%2Fcdn.vox-cdn.com%2Fuploads%2Fchorus_asset%2Ffile%2F25584373%2F247226_AI_Pixel_Reality_CVirginia_3.jpg?width=92&height=&ar=&mode=&format=avif&dpr=2){kind=tracking}
No one’s ready for this
The photograph is now meaningless as evidence. We are not prepared.
Fine-tuning now available for GPT-4o
Fine-tune custom versions of GPT-4o to increase performance and accuracy for your applications
light-the-torch
`light-the-torch` is a small utility that wraps `pip` to ease the installation process for PyTorch distributions like `torch`, `torchvision`, `torchaudio`, and so on as well as third-party packages that …
AI in Journalism Futures 2024
https://www.opensocietyfoundations.org/publications/ai-in-journalism-futures-2024 [Open Society Foundations] "In February 2024, the Open Society Foundations issued a call for applications for a convening in which selected participants would share their
The dangers of AI agents unfurling hyperlinks and what to do about it · Embrace The Red
Automatically unfurling hyperlinks can lead to data exfiltration. This post shows how to mitigate this threat in Slack Apps
SQL injection-like attack on LLMs with special tokens
Andrej Karpathy explains something that's been confusing me for the best part of a year: The decision by LLM tokenizers to parse special tokens in the input string (``, …
Deception abilities emerged in large language models | Proceedings of the National Academy of Sciences
Large language models (LLMs) are currently at the forefront of intertwining AI systems
with human communication and everyday life. Thus, aligning t...
Journal of Chemical Information and Modeling
Read research published in the Journal of Chemical Information and Modeling Vol. 64 Issue 7 on ACS Publications, a trusted source for peer-reviewed journals.
GitHub - NirDiamant/RAG_Techniques: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont...
AI has all the answers – even the wrong ones
Can large language models solve logic puzzles? There’s one way to find out, which is to ask. That’s what Fernando Perez-Cruz and Hyun Song Shin recently did. (Perez-Cruz is an engineer; Shin is the…
MIT releases comprehensive database of AI risks
Researchers at MIT have released the AI Risk Repository, a comprehensive database that can help organizations identify and mitigate AI risks.
Would LLMs democratizing coding be a pyrrhic victory?
One Useful Thing | Ethan Mollick | Substack
Trying to understand the implications of AI for work, education, and life. By Prof. Ethan Mollick. Click to read One Useful Thing, by Ethan Mollick, a Substack publication with hundreds of thousands of subscribers.
Mapping the misuse of generative AI
New research analyzes the misuse of multimodal generative AI today, in order to help build safer and more responsible technologies
Transformer Explainer
Black Forest Labs - Frontier AI Lab
Amazing AI models from the Black Forest.
GPT-4o System Card
There are some fascinating new details in this lengthy report outlining the safety work carried out prior to the release of GPT-4o. A few highlights that stood out to me. …
q What do I title this article?
Braggoscope Prompts
Matt Webb's [Braggoscope](https://www.braggoscope.com/) ([previously](https://simonwillison.net/2023/Feb/13/braggoscope/)) is an alternative way to browse the archive's of the BBC's long-running radio series [In Our Time](https://www.bbc.co.uk/programmes/b006qykl), including the ability to browse by Dewey Decimal library …
Why I Lost Faith in Kagi
Issues with Kagi's AI focus, finances and leadership
Extracting Prompts by Inverting LLM Outputs
We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box method,...
How I Use "AI"
I don't think that AI models (by which I mean: large language models) are over-hyped. In this post I will list 50 ways I've used them.
How I Use “AI” by Nicholas Carlini
Nicholas is an author on [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://arxiv.org/abs/2307.15043), one of my favorite LLM security papers from last year. He understands the flaws in this …
Introducing sqlite-vec v0.1.0: a vector search SQLite extension that runs everywhere
Install with Python, Node.js, Deno, Bun Rust, Go, C, WASM...
We had an AI attempt to make a data-driven story like we do at The Pudding
We review and grade what it created.
Aider
Aider is an impressive open source local coding chat assistant terminal application, developed by Paul Gauthier (founding CTO of [Inktomi](https://en.wikipedia.org/wiki/Inktomi) back in [1996-2000](https://www.linkedin.com/in/paulgauthier/details/experience/)). I tried it out today, using an …
Doctors weaponize AI in insurance battles over patient care authorizations
Physicians are pushing back against automatic denials from healthcare insurance providers by allowing AI tools to write their appeals.
Non-Obvious Prompt Engineering Guide
There are many prompt writing tutorials available. In this one, I share unique insights not found elsewhere.