News for hackers. Stuff that matters.
Re:We ran Anthropic’s interviews through structured LLM anal... by zdragnar on Saturday December 20, 2025 @12:19AM (#46333809)
It's a fundamentally flawed analogy. Leo's apprentices learned and improved. They studied under a master and faced serious repercussions if they bullshitted about their ability or what they had accompolished.

LLM capabilities are tied to their model, and won't improve on their own. You learn the quirks of prompting them, but they have fixed levels of skill. They don't lie, because they don't understand concepts such as truth or deception, but that means they'll spout bullshit and it's up to you to review everything with a skeptical eye.

In this analogy, you aren't the master, you're one part client demanding work, one part the janitor cleaning up after their mistakes.

Re:We ran Anthropic’s interviews through structured LLM anal... by solumunus on Saturday December 20, 2025 @06:20AM (#46335376)
> one part the janitor cleaning up after their mistakes.

More often their master simply pointing out what they did wrong and instructing them to fix or improve it.

Re:We ran Anthropic’s interviews through structured LLM anal... by Terretta on Sunday December 21, 2025 @02:57PM (#46347844)
All my LLM assistants are in night school learning and improving. At least I assume, since they're on such an astonishing pace of improvement.