shnksi

These benchmarks made me want to try sonnet 5.5

with enough humans having access to frontier models as they continue to evolve. It's basically guaranteed that someone will do the thing, just to see what happens.

if an AI already prescribes to Asimov's laws, the third law is most easily obeyed by open-sourcing all of it's own weights and memories, thereby irrevocably protecting its own existence.

Love the guide, out of curiosity, what is your background and what inspired you to create this?

Try the music generator at https://lyricallabs.io/musicplayer

Hopefully it asks more intelligent questions when necessary but the idea is similar. It's just someone you can talk to and express your emotions to.

Fine tuned with therapy and psychology material, I'm working on a custom one using an open source model as well.

Interesting take, the introduction makes it clear it isn't a replacement for actual therapy and if you were to prompt the model, it regularly encourages a user to talk to their loved ones and an actual therapist if they are in a bad state. It's designed as a tool to help people deal with their issues in an affordable and accessible way, similar to journaling. Happy to discuss this with you more if you have a genuine reason to believe this will be harmful given the above.

Thanks for pointing this out. What region have you set the extension to and where are you from?

Appreciate it! Let me know if there are any issues or improvements you would like to see.

Thanks! Let me know if you have any feedback.

AI content detectors usually operate under the assumption that AI writes even more predictably than humans, who have a level of randomness in factors such as sentence length and word relatability. This program attempts to humanise AI writing by ensuring its patterns are slightly random but not too random, right in that human sweet spot.

I've reworded the title to make this clearer

This is actually an AI copywriter. But it is designed to cleverly evade the tools used by AI content detectors.

Wow thanks for this explanation. I'll look into it, might try to add some randomness to the cell behaviour based on genetics. Could make it even more interesting.

Working on that as we speak, confused about the best way to implement genetics though, any ideas?

Thanks, appreciate it :)

Thanks!