xrendan

I would absolutely love if you brought Canadian maps to this.

I work for Build Canada and I would love to see some maps from the fur trade and early exploration to tell stories.

If you want to chat my email is brendan at buildcanada.com

One thing that has surprised me (and I should've known that it wasn't great at it), but it is terrible at creating bounding boxes around things it's not trained on (like bounding parts on a PCB schematic.)

Amazon - Ecommerce (1994), AWS (2006)

Microsoft - Programming Language (1975), Operating Systems (1981), Office Suite (1983)

Meta - Facebook (2004), Instagram (2010)

I would argue microsoft is unique because of how badly IBM screwed up.

I read that as the size of file it's transferring so each operation would be bigger and therefore slower

Ugh, I don't have it. It was from before I used git.

Basically to do this you have a cups server that exposes itself as a network printer that prints to a specified PDF directory and then you have a program watching that directory for new files and if there's a new one it opens up whatever pdf viewer you want in full screen.

Setup a shared pdf printer: https://askubuntu.com/questions/1310867/how-to-set-up-shared...

I have some really old code that pretty much does this, I'll see if I can find it.

I love the Blueprint Understanding.

One thing I've been thinking about is if you could use a model like this as the first pass for permitters (Like a GitHub Actions CI/CD) who review blueprints.

Many developers use the regulatory side of various engineering approval processes as a quality control check which costs money and time for the regulator who is tasked with enforcing a standard.

It would also be good to speed up the workflow for developers saying hey, this thing looks weird did you really mean to do this?

And then further on, you could add a way to check it for constructability. My framer friends often get annoyed at whatever engineer because the way the structure is designed is materially inefficient or hard to construct.

You're misreading it, there's two different runs, a low and a high compute run.

The number for the high-compute one is ~172x the first one according to the article so ~=$2900

Azure charges differently based on deployment zone/latency guarantees, OpenAI doesn't let you pick your zone so it's equivalent to the Global Standard deployment (which is the same cost).

[0] https://azure.microsoft.com/en-us/pricing/details/cognitive-...

I'd be interested in knowing if anyone is seriously using the assistants API, it feels like such a lock in to OpenAIs platform when your can alternatively just use completions that are much more easily interchanged.

This generally resonates with what we've found. Some colour based on our experiences.

It's worth spending a lot of time thinking about what a successful LLM call actually looks like for your particular use case. That doesn't have to be a strict validation set `% prompts answered correctly` is good for some of the simpler prompts, but especially as they grow and handle more complex use cases that breaks down. In an ideal world

> chain-of-thought has a speed/cost vs. accuracy trade-off a big one.

Observability is super important and we've come to the same conclusion of building that internally.

> Fine-tune your model

Do this for cost and speed reasons rather than to improve accuracy. There are decent providers (like Openpipe, relatively happy customer, not associated) who will handle the hard work for you.

I use this all the time and you can copy a range of values with multiple cursors and then paste them into the same size range. It's nice for hashes or modifying static lists that all need the same changes, but are annoying to regex for

The Diff [0] and Capital Gains [1][2] by Byrne Hobert are excellent.

If you're interested in in-depth analysis of current events in finance, tech and other related musings.

Capital Gains is more focused on ideas in finance and how to think about them.

[0] https://www.thediff.co/ [1] (With referral code) https://capitalgains.thediff.co/subscribe?ref=zlPGzwicD7 [2] (Without referral code) https://capitalgains.thediff.co/subscribe

I'm generally interested, but it would be helpful to understand what the different plans are actually offering? I have no idea what the difference is between:

- Starter Developer Bot - Pro Developer Bot - Enterprise Developer Bot

Also, the music on your demo video is a bit excessive, I don't really expect hype music when I'm looking at a demo. It would be more helpful to have someone talking explaining what's going on (or silence)

Is it possible to join those data sources against an existing database like MySQL or SQLServer?

I have a cluster using terraform-hcloud-kube-hetzner [0] and I'm quite happy with it.

It uses MicroOS for rolling releases and auto-upgrades for less maintenance. I'm quite happy with it so far, and I like that it integrates with terraform.

[0] https://github.com/kube-hetzner/terraform-hcloud-kube-hetzne...

A big reason that Ontario can't / doesn't is that the demand centers in Southern Ontario are ridiculously far from the generation centers in Manitoba. Toronto is 1800 km straight from the new Keeyask Dam. This is over unpopulated muskeg that is expensive to build on in the first place and difficult to access for maintenance.

It just crashes after finishing onaboarding trying to load with:

TypeError: can't access property "push", Mo['ex-Unicorn Founder'] is undefined

What's the sort of timeline on GIS extensions? Great work btw, I've been following since the alphas and I'm excited to try it out :)

I think it really depends on the application of web scraping. (As someone who does, what is in my mind, ethical web scraping)

- Scraping public information from government websites to do analysis: ethical, it's the public's data

- Scraping to help some companies customers more effectively use that companies product, for example scraping a medical office's insurance claims to help them automate their insurance remittance process: ethical

- Scraping faces to build a surveillance-tech company: disgusting

- Scraping your own website because your internal processes are so broken you can't get it any other way: ethical

- Scraping to just copy someone's data they worked hard to generate to go and resell: unethical

Depending on your use-case (if it's read heavy), you could use SQLite hosted on R2 being read by workers

Yes, but you need to detect the fakes before you can ban them. An adversary could just rotate camera keys before they're even detected.

The see an example button on the home page just refreshes the page on both Firefox and Chrome for me on Linux

It's not true that all government power belongs to the federal government and that provinces only gain power by devolution from the federal government. The Canadian constitution describes areas of responsibility for both the federal and provincial governments with some shared areas of responsibility.

Do you know what the big difference for companies to cram enough hardware into the same space to support 20W power like Anker [1] Is this just incremental improvements or is there a technological breakthrough that's enabled this?

[1] https://us.anker.com/pages/uai2020

In my province (Alberta) I'm allowed to carry digital proof of insurance for my car instead of the standard pink sheet. The app has a mode that displays the insurance info on the lockscreen while locking the rest of the phone to the police (or whoever else needs to see it). So there are technical solutions to the first issue.

The second issue, I completely agree, I would rather the system be an addition to existing IDs rather than a replacement to them.

There's also https://firesmoke.ca

I set up a meeting for tomorrow through your website (look for a meeting with Brendan), we've got a large use case for this and it could really help us out.

Follow-up question, can I screenshot webpages that it visits?

Is there any capability to run bots headless on our own infrastructure as opposed to locally?