Viewing profile — UltraLutra

It’s not bad for summarizing or translating. I like categorize AI outputs by prompt + context input information size vs output information size. Summaries: output Translate: output…

* And you’re probably costing Anthropic >$1k in inference costs per _week_. Not >$10k. Typo.

> Claude is simply too good at coding in well-represented languages like Python and Typescript to not pay hundreds of dollars a month for (if not thousands, subsidized by employers…

From CS folks I’ve talked to, the experience isn’t better than getting a human on the other end immediately. It’s better than not being able to reach a human (e.g. outside support …

It’s cute they think managers are evaluated on the quality of their employee performance review. I don’t disagree with the content. A well-thought review will help employees perfor…

> …so it is hard to explain why their kids would be better off knowing something they don't need. Math is full of extremely useful concepts that aren’t otherwise obvious. To me, it…

Yep. I work in finance. There are a ton of things like this that are just convention. Like treasury bonds being priced in 1/32nd increments. It probably made sense at the beginning…

I'm not in anyway an expert, so I googled what some research says. Here's an interesting meta-analysis ( https://link.springer.com/article/10.3758/s13423-023-02303-4 ). Memory and …

[dead]