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

To be fair (as one who leans pretty heavy in favor of the JS world) .padStart() was only added in response to the aforementioned left-pad fiasco. The language adding that was more a face saving measure from the blowback than an attempt to fix the actual problems.

Despite all that, left-pad still gets > 1 million weekly downloads on npm.

big fan of the approach & simplicity!

Thank you!

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...

Wish this had a web ui.

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.

So your theory would have it that if you repeated the question at temp 1 it would give the wrong answer more often than the correct answer?

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.

> Temperature 0 is the correct evaluation.

In theory maybe, but I don't think it is in practice. It feels like each model has its own quasi-optimal temperature and other settings at which it performs vastly better. Sort of like a particle filter that must do random sampling to find the optimal solution.

Here's a quick analysis of the model vs it's peers:

https://www.youtube.com/watch?v=ReO2CWBpUYk

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.

There you go, GPL, now we're talking.

I understand that people gotta make money, but giving access to something as insanely critical as a company private repo... it's either a huge company the lawyers can talk to, or this.

Open source.

Definitely checking out codemancer.

Although it has a mention of "GPL" at the bottom of the readme in your repo:

https://github.com/0xmmo/codemancer/

... it doesn't have anything else.

Generally the text of the GPL license is placed in a file (named "COPYING" or "LICENSE") in the root directory of the repo. Might want to add it so its super clear. :)

Thank you for the tip! Will add.

Have you checked out aider-chat? Seems very similar to what you're working on.

Couldn't agree more! Codemancer looks great, I'll give it a try

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?

You have to be very careful here. The payments are a problem. Maybe obtain a concurrent part-time H-1B through your company.

Last I used Amplitude it was insanely expensive. Is that not still the case?

We’re working on it! Free up to 10M events, more to come later this year.

What would reasonably costed look like to you?

More on my view on real-time analytics here: https://news.ycombinator.com/item?id=15380607

I need to remember that on HN, sometimes the founders of companies I'm talking about will respond :D. I should've used more words.

I don't really know what reasonably costed would've looked like for the time I used Amplitude (2018-2019), but I know that the value my team extracted from it was not commensurate with its cost. Whether that was because of overzealous assumptions on our part, or something else, I don't really know, but I know we signed up, used for a few months and then canceled/downgraded to a cheaper service whose name is escaping me.

I was mostly challenging the "Just use ____" notion of the commenter above, not really that Amplitude is worth the money for correctly-intentioned businesses. Regardless I appreciate the ask.

real-time, good, cheap. pick two.

At best it's pick two. Often you get one or none.

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.