This site will let you test different GPTs (far from all of them, but its a good list) in various ways. I particularly like the Arena, in which you get responses from 2 random models to your input, you say which you like best, and then it tells you which is which.
It’s got me considering Claude2 for local projects. I just need to revive the hardware I’d use to run it on.
I think this varies by country, so you may need to specify where you’re at. For instance, I noticed that content on Hulu in the U.S. was being advertised as available on Disney+ in Canada, like the miniseries they did on Pamela Anderson and Tommy Lee and their sex tape. I don’t think that would ever fit with the Disney brand in the U.S., which is supposed to be very family-oriented, so they use a different brand for more adult stuff.
Uncensored Llama2 70B has the most flexibility as far as a model without training IMO. The mixtral 8×7B is a close second with faster inference and only minor technical issues compared to the 70B. I don’t like the tone of mixtral’s alignment.
Depending on what you meant by this question, I’d say Perplexity. It’s got access to a number of different LLMs, and cited its sources. The biggest concern I’ve had when it comes to LLMs is that they eventually make shit up. If you can verify its answers by checking its sources, you have a much higher confidence level in the answer.
The most productive thing I used the free ChatGPT web was to expand a Python 3 script that I was using to run a custom ChatGPT with a Gradio web ui that worked with OpenAI’s API.
I learned quite a lot of Python from almost zero and improved the script to work with LangChain Tools, for instance with a custom recursive summarizer.
ToonStruck, remastered, or the shelved sequel ressurected. I’d like Burst to (exist again and) handle the development because they did a fantastic job the first time around!
asklemmy
Oldest
This magazine is from a federated server and may be incomplete. Browse more on the original instance.