callmeed

Joined 18 years ago

Karma
9,582
Submissions
2,719
Member since
Apr 23
Erik Dungan

Location: San Luis Obispo, California

Senior Engineering Manager at Indeed

(previously Interviewed.com YC S15)

Ruby, Rails, iOS, Javascript. I also like to take pictures and cook food. Opinions expressed here are mine (and probably wrong).

Get in touch:

twitter/Github/Instagram: @callmeed

erik[dot]dungan[at]gmail[dot]com

View on Hacker News

Recent submissions

Comment · 9 months ago
Maybe I need to punish tab/windows switches more severely?

Or perhaps require webcam and do eye tracking?

Comment · 9 months ago
School/students were my target user when I created this. But also mostly just a fun toy.
Comment · 9 months ago
That's cool, thanks for sharing.

Is there a way to detect this approach?

Comment · 2 years ago
Ok, that's helpful but I'd argue even a limit order book has an algorithm (albeit simple)
Comment · 2 years ago
Comment · 2 years ago
+1 I use chartjs for the web version of fatgpt.ai. It easy to setup and you can get charts going very quickly.

If I needed more dense data viz (ex a datadog-like system) I'd probably go with something D3 based

Comment · 2 years ago
It's interesting, seems like a popular space lately (even within YC). Off the top of my head, there's merge.dev, Terra, Kombo, Workato.

Aside from the obvious question of "how are you different/better?" I'm most curious to know why you're going so broad initially. You've got everything from legal to devtools to gaming. Seems like the opposite of a wedge/beachhead approach. Why?

Comment · 2 years ago
I was somewhat involved in this project. Can't get into details but there were other factors/efforts not mentioned which allowed us to scale this while reducing cost per recommendation. As someone mentioned, I do believe we benefited from a price drop over time.

Regarding the monthly scale mentioned in article–we are way beyond that now.

A lot of really smart people worked on this and it was fun to watch unfold.

Comment · 2 years ago
Transformers that transform your body
Comment · 2 years ago
Jokes aside, GPT-4 Vision is surprisingly good at noticing facts from food images. For example:

- In my chipotle bowl, it can tell if I had brown rice vs white rice

- In my In-n-out, it can tell if I got it protein style

It struggles with accurate weights/volumes but I'm excited about where this is going.

Comment · 2 years ago
I'm building a weight-loss app that leverages LLM to do 2 things:

1. Analyze calories/macronutrients from a text description or photo

2. Provide onboarding/feedback/conversations like you'd get from a nutritionist

https://www.fatgpt.ai/

My stack is Ruby on Rails, PostgreSQL, OpenAI APIs. I chose Rails because I'm very fast in it, but I've found the combination of Rails+Sidekiq+ActionCable is really nice for building conversational experiences on the web. If I stick with this, I'll probably need a native iOS app though.

Vendor stack is: GitHub, Heroku (compute), Neon (DB), Loops.so (email), PostHog (analytics), Honeybadger (errors), and Linear.

Comment · 2 years ago
I mean a single checkout from multiple shopify stores isn't really possible (at least by 3rd parties)

My hypothesis is that, if you could drive traffic to your site and offer a fast checkout experience, there's probably multiple ways to monetize that. Driving the traffic is the hard part.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton