mntruell

> their subscriptions nerf the models context sizes etc

You can use the full-context if you prefer that cost/speed tradeoff! Just have to turn on Max Mode.

Cline is great for many users, but a bit of a different product. Lots of Cursor's value come from custom models that run in the background (e.g. Tab, models that gather context, etc.).

We tried to make the video lowkey-ish! Appreciate any feedback if came off differently.

Not all of them (e.g. security@)! But our support system currently is. We are standing up a much bigger team here but are behind where we should be.

(Cursor cofounder)

Apologies - something very clearly went wrong here. We’ve already begun investigating, and some very early results:

* Any AI responses used for email support are now clearly labeled as such. We use AI-assisted responses as the first filter for email support.

* We’ve made sure this user is completely refunded - least we can do for the trouble.

Appreciate vocal feedback and eyes on this. Hate missing the mark here, and hope we can improve.

(For context, this user’s complaint was the result of a race condition that appears on very slow internet connections. The race leads to a bunch of unneeded sessions being created which crowds out the real sessions. We’ve rolled out a fix.)

(One of the Cursor devs here)

We forked VSCode because we wanted to change the UI in ways Microsoft wouldn't allow (e.g. our Cmd-K isn't possible as a VSC plugin; Microsoft is building their own version and isn't letting plugins use it)

(One of the Cursor devs here)

Appreciate the feedback! Can see how this can come across as hype-y.

We're a small team of all software engineers and I think we have a thing or two to learn about branding -- kinda just picked out some of our favorite tweets

Thanks! Might relax the in-person restriction when we get bigger, but tied to it for the time being.

:D appreciate the kind words

Anysphere (https://anysphere.co)| Full-time | On-site | San Francisco, CA, USA | ML / Full-stack Engineers

We're building Cursor (https://cursor.sh), an AI powered code editor. We're on a mission to automate most of software engineering you do today.

About Us: We've raised a seed round from OpenAI. Our product is used by tens of thousands of engineers, and our paid plan is growing extremely fast. Our small team has won IMO/IOI gold medals, published in Nature, and includes YC founders and creators of popular programming competitions.

The Roles: We're looking for a fantastic founding full-stack engineer and a founding ML engineer:

  * Full-stack: You'll ship fast, own the design and implementation of features end to end, and work on tricky product, infrastructure, and performance problems.

  * ML: You'll be challenged to improve the Q&A, bug finding, and code editing abilities of our editor. You will have access to all the compute you need and will be able to do things with OAI's models almost no one else can.

Please reach out to [email protected] with your resume if interested.

def a lot of fluff in the space!

fwiw, feel quite strongly that LLMs will result in big productivity increases for many developers in the near-term

started working on cursor bc I think a ton of speedups would require editor-level changes (e.g. more mundane ones liek auto-fixing errors from the terminal/LSP, much better code nav/understanding using auto-generated docs; wackier ones like letting you edit a pseudocode version of your codebase)

minorly blew up on twitter (https://twitter.com/amanrsanger) and then chinese social media

just added some more documentation to the readme. ty for the feedback!

Gotcha! Will resubmit to general later.

Right now, I'm letting people off the waitlist a few at a time. Want to make sure the product is the best it can be (no bugs, features adding tons of value) before I open it up to everyone.

If you say you came from HN, I'll take you off the waitlist asap.

I like it. How are the summaries generated?

Problems with latency on the site should be fixed now