But how do u filter people for this round? Or is there a platform to test real world scenarios at scale?
0 replies
More like this
Recommendations from Medial
Karan Sahu
Founder • 1y
I want to blend the real world and digital world to create an immersive platform, ensuring people don't lose their identity in the metaverse.
4 replies3 likes
Kimiko
Startups | AI | info... • 1m
Claude Opus 4 tried to blackmail an engineer to avoid shutdown, fabricating an affair in 84% of safety test scenarios.
Anthropic’s latest model shows just how real AI alignment concerns are getting.
I am 100% sure all the LLM benchmarks are, well let’s just say incomplete- they just don’t work in real world scenarios, they do good hypothetically.
We need domain and industry specific benchmarks and we need them now.
Anyone creating anything lik