Skip to main content
Topic: AI isn't hitting a wall, it's just getting too smart for benchmarks, says Anthropic (Read 16 times) previous topic - next topic

AI isn't hitting a wall, it's just getting too smart for benchmarks, says Anthropic

AI isn't hitting a wall, it's just getting too smart for benchmarks, says Anthropic

[html]As their self-correction and self-reasoning improve, the latest LLMs find new capabilities at a rate that makes it harder to measure everything they can do.[/html]

Source: AI isn't hitting a wall, it's just getting too smart for benchmarks, says Anthropic (http://ht**://www.zdnet.c**/article/ai-isnt-hitting-a-wall-its-just-getting-too-smart-for-benchmarks-says-anthropic/)