Nice! We started from a pretty similar idea, about 11 months ago. Just shipped [https://space.apesonfire.com this week.
The AIs are now no longer just debating each other. But we are running 1000s of those debates (essentially brainstormings) in parallel and let the lead model evaluate over each of the result sets. Try our “Spark” agent for a quick developer preview.
> Grok exhibits a noticeable bias toward portraying Elon Musk favorably by overemphasizing "no evidence" and downplaying controversies—Perplexity, Claude, and DeepSeek correctly highlight this pattern over Grok's denial.
Fair point – that's exactly the kind of thing we built this for. Seeing multiple AIs cross-check each other in real time makes biases way more visible than asking them one by one. Cool it's working as intended.
By the way, try using '@' mentions when you want to tag specific AIs – makes it way easier to direct questions and keeps conversations cleaner. Thanks for the feedback!
Ha I was being tongue in cheek for sure but not as a critique of the site just about Grok. I had a lot of fun with this tool last night. Very interesting watching the process play out and just a cool idea, already shared with a few buddies. Good to know about the @!
Congrats and have a wonderful Christmas if you celebrate :)
Thanks so much! Really glad you had fun with it and shared with friends. Dropping an update tonight - should make the app even better. Merry Christmas!
Nice! We started from a pretty similar idea, about 11 months ago. Just shipped [https://space.apesonfire.com this week.
The AIs are now no longer just debating each other. But we are running 1000s of those debates (essentially brainstormings) in parallel and let the lead model evaluate over each of the result sets. Try our “Spark” agent for a quick developer preview.
> Grok exhibits a noticeable bias toward portraying Elon Musk favorably by overemphasizing "no evidence" and downplaying controversies—Perplexity, Claude, and DeepSeek correctly highlight this pattern over Grok's denial.
Definitely works!
Fair point – that's exactly the kind of thing we built this for. Seeing multiple AIs cross-check each other in real time makes biases way more visible than asking them one by one. Cool it's working as intended.
By the way, try using '@' mentions when you want to tag specific AIs – makes it way easier to direct questions and keeps conversations cleaner. Thanks for the feedback!
Ha I was being tongue in cheek for sure but not as a critique of the site just about Grok. I had a lot of fun with this tool last night. Very interesting watching the process play out and just a cool idea, already shared with a few buddies. Good to know about the @!
Congrats and have a wonderful Christmas if you celebrate :)
Thanks so much! Really glad you had fun with it and shared with friends. Dropping an update tonight - should make the app even better. Merry Christmas!