Funny of this to come out from LangChain.

yeah you can simply replace mcp with langchain and have a new article

go install github.com/sinclairtarget/git-who@latest

Do they have the solution (I'd assume Supermaven which they recently acquired does) and are they just giving out an interesting challenge to readers? Or... what is this?

Clinic.js was promising but it's not maintained anymore, would be great if we had a modern alternative: https://clinicjs.org/

Do you have an example prompt that works?

Hey, yes it draws a lot of inspiration from mitata, but it's much tinier and with less features. I remember I was getting some less accurate measurements in browsers when I tried it (~2 years ago) and I decided to build my own and got the results I expected.

Mitata has added a ton of things since then and it's very mature, and it's built by evan so it's definitely the right choice over benchmate. I used benchmate because I can easily extend it to support the upcoming features in BenchJS.

BenchJS is for easily building shareable benchmarks, and I want to evolve it into a nice code analysis tool. It uses Babel and esbuild to transform and bundle the code before it gets evaluated, and I want to use this to extract more useful insights like the number of operations of a given type (ex. array methods), code path analysis (coverage-like), inline indicators of how much % time a line took, etc.

Beware that you are spreading malware through https://git.makr.io/

Appreciate the heads up! For my learning, what do you mean? The projects themselves from GitHub surfaced here or the website?

I think I understand the issue, the homepage random trending repos. Took offline for now.

Let me know if something different.

Pretty underwhelming, I've been using on Kagi's assistant [0] for the past few months and it's much better. I can `!chat what i want to search for` in my address bar any time, and Kagi will do the search and then open a chat with the LLM of my choice (3.5 Sonnet) and the results in context. It can also do further searches.

[0] https://kagi.com/assistant

Second this, Assistant is a game-changer for me. Its the usefulness of AI with footnotes that give me confidence that I can know where that came from and if I trust it. Especially for product reviews, being able to use lenses that filter out sites I don't trust and then run AI on top of it is pretty cool.

>Its the usefulness of AI with footnotes that give me confidence that I can know where that came from and if I trust it.

I have been using http://www.Perplexity.AI since January 2023 for this exact reason. Unfortunately, since that incredible first UI (of yesteryear) it has been downgraded extensively (including no longer displaying footnotes, just adding numerals to the ends of factual sentences with tooltips).

The greatest thing about Perplexity is still that you do not have to log in (although it will bug you, particularly after lengthier or insightful conversations). Once a search/hybrid/chatGPT (how I've used it for almost yearS now) requires a log-in, it will immediately not be able to compete well with open-facing search engines like Google.

I have this same hesitation about using a pay search engine like Kagi, but am definitely intrigued by some of the other commenters' descriptions of the AI Assistant part of their service offering.

Do you use the ultimate package? How are the rate limits if so?

made one as well with interactive selection and token counting https://github.com/3rd/promptpack