LLMs for friends, family & more
This is a joint project with Val Natanelov.
Large Language Models (LLMs) are the most exciting technology I have witnessed since becoming a thinking adult. They are useful for so many things, and so learning to use them is key to thriving in today’s world. In the same way knowing how to use a search engine was an important skill before LLMs, knowing how to use LLMs is crucial skill after they came out.
Get access
I want to support you in learning to use LLMs safely, while giving you the ability to try out all the new models and tools as they are coming out in a coherent and easy way.
To get started, click the following button:
Click on “Sign up”, and fill in your name/email/password, and verify your email. Once you’ve done that, message me on Signal and I’ll approve your account!
Philosophy
The idea of this project is that we (Val and I) are really interested in LLMs: we think they are super useful and just awesome technology in general. We spend way too much time learning about them and being on top of everything going on in that world. We want to help you figure this stuff out too (because we think it’s an essential skill) without having to spend that inordinate amount of time on it. In exchange hopefully you can help us get a better understanding on how different types of people use them and what they find them useful for. We also don’t really know where Axess-AI.com is going right now, maybe this is a useful thing and it might grow bigger.
How it works
We curate a selection of the best (and sometimes interesting/different) models, then hook them up to Axess-AI.com via the providers’ APIs to allow you to use them. Currently we provide access to the leading models from OpenAI, Anthropic, Google, Meta, and so on. You can seamlessly switch between models (even mid-conversation), and even modify LLM parameters and the system prompt, there’s a lot of other features as well.
As part of curating the models, we tag them in a way that we think makes sense and helps you pick a good model for your use case. This changes all the time as the LLM landscape changes, but you can read more about the available models and how we’ve categorized them right now on our docs site.
Privacy while using LLMs
Lots of people are wary of using LLMs because they’re afraid their data will be misused by the companies building the models. Sometimes this is warranted such as with free providers that explicitly use your data for training (e.g. free ChatGPT, free Meta.ai, etc).
All providers available on our platform contractually agree not to use your chats for training their models, and to not store chat logs (except temporarily for anti-abuse, etc). You are not the product: we pay real money to use these APIs.
In our judgement, the LLMs through our platform are safe to use for normal everyday tasks, similar in vein to how you use other platforms that are not end-to-end encrypted (e.g. social media, email, etc). We use these LLMs for all kinds of tasks including those that involve personal information (names, addresses, details, etc). Still, LLMs are not end-to-end encrypted, and we recommend not using them for extremely sensitive matters (the kinds of things that you would not do outside end-to-end encrypted platforms like Signal).
Your chats are stored on our servers so that we can provide you the service. We don’t have direct access to them and will only use them to produce usage and cost statistics.