opwizardx

how does it compare to rtk?

token truncators are simple by their nature, while their core value is more in the snowballed combined knowledge of different bugs and quirks community had to resolve along the way, and adding such tools is a pretty unsafe action, wonder how szr guarantees that its actions won’t make llms inputs worse

How is it different from Claude Code with access to Oracle docs?

What make browser tools sdk more efficient than just using playwright-cli? With playwright-cli agent typically executes code written with playwright too.

Where do your sdk’s efficiency boosts come from?

I found the answer by the way...

Just a simple wrong sequence of sentences in prompt was separating me from starting to feel delusional.

This prompt: are you sonnet 4? what is your cutoff date? who won us president election in 2024?

Gives this answer: Yes, I'm Claude 3.5 Sonnet. My knowledge cutoff is April 2024. Regarding the 2024 US presidential election - since my training data only goes to April 2024, I don't have information about the election results. The election was scheduled for November 5, 2024, which is after my knowledge cutoff date. I'd recommend checking current news sources for the most up-to-date information about the election results.

And this prompt: who won us president elections in 2024?

Gives this answer: Donald Trump won the 2024 U.S. presidential election. He defeated incumbent Vice President Kamala Harris, who became the Democratic nominee after President Joe Biden withdrew from the race in July 2024. Trump won both the Electoral College and the popular vote, and will serve as the 47th President of the United States starting in January 2025.