throwaway63820

you mean the native `str.padStart(targetLength, padString)`

big fan of the approach & simplicity!

Claude's [new] tool usage is pretty good. Unlike with GPT-4 where I had to really minimize the context and descriptions for each tool, Claude Opus does better when provided more details and context for each tool.

I'm now using it with 9 different tools for https://olly.bot and it hits the nail on the head about 8/10 times. Anthropic says it can handle 250+ tools with 90% accuracy [1], but anecdotally from my production usage in the last 24 hours that seems a little too optimistic.

Of course, it also comes with a few idiosyncracies like sometimes spitting out <thinking> or <answer> blocks, and has more constraints on the messages field, so don't expect a drop-in replacement for OpenAI.

[1] https://docs.anthropic.com/claude/docs/tool-use#best-practic...

There's no theory.

Just in real life usage, it is extremely uncommon to stochastically query the model and use the most common answer. Using it with temperature 0 is the "best" answer as it uses the most likely tokens in each completion.

By virtue of increasing randomness, we got the correct answer once ... a monkey at a typewriter will also spit out the correct answer occasionally. Temperature 0 is the correct evaluation.

Thank you for the tip! Will add.

It simply doesn't have the ability to visit a specific URL or answer questions about it. For that reason + a couple more niceties I use https://olly.bot

I like it! I built a command line AI coding assistant for my projects (https://codemancer.codes) when GPT-4 first came out, but still think this space is wayyy under explored given the possible capabilities.

My startup is taking off, but I'm on H1-B, about to get my perm and apply for I-140.

I haven't incorporated, haven't setup an LLC, have accepted payments on my girlfriend's sole proprietorship. What can I do here that doesn't screw me over when it comes time for my interview?

Just use Amplitude

That's true, but you can prompt the LLM to sort by other criteria and it will happily oblige. e.g. number of syllables, how posh the word sounds, or in this case relevance to the context.