kami8845

Same here. Using it this week and on Thursday I began to understand why Lee Sedol retired not long after being defeated by AlphaGo. For the stuff I'm good at, 3 months ago I was better than the models. Today, I'm not sure.

Amazing to see the scale of it. As a piece of feedback my assumption is that different officers are assigned to different areas and so since street sweeping is either the first and third or second and fourth week of the month for most residential areas, this will allow different officers to float to the top in different weeks. Having at least a 2 week lookback for the leaderboard is probably best. Otherwise great work!

In my experience they are rarely used, unless you are stopping over in Ireland or Iceland.

Same here, the experience has been generally favorable.

yeah unfortunately the OpenAI API hangs sometimet

I think their lead might be a bit bigger than that. ChatGPT 3.5 was released 4 months ago and I still haven't seen another LLM come close to it.

This is a good point I'll add!

will do!

Haha, I'll set up a docker image that people can pull down!

Hey! You can edit past messages you've submitted and they will generate a new response that overwrites whatever happened in the conversation previously. If you're talking about a tree-like struct where you can have different branches, then true, only the official UI has it AFAIK :)

GPT3.5 Turbo pricing is 10k tokens or ~7500 words for $0.02. Though note that every API request includes the entire chat context and charges for input & output tokens. https://openai.com/pricing

Editing the prompts (which are currently submitted via the system message similar to your linked app) is a great idea. I'll add it to the to-do list :)

GPT-4 is decently more expensive -- I personally really like & use the therapist character a lot. In this scenario the session would cost me less than $1 which is still much cheaper than any therapist I've used previously :)

Hey, run locally in this case means: YakGPT has no backend. Whether you use the react app through https://yakgpt.vercel.app/ or run it on your own machine, I store none of your data. I will try and make this wording clearer!

Hey! I would love to. I seriously considered adding my own key into the app, and implementing some rate limiting to e.g. allow you to send 3 messages for free. But unfortunately that would require me to store some backend data on you that I do not want: I want this to be a completely "private" / FE-only application that stores no data on anyone.

Hey! I definitely understand the reservation. This is definitely me as well. My reasons for using the UI at this point:

* GPT-4 is decently faster when talking straight to the API

* The API is so stupidly cheap that it's basically a rounding error for me. Half an hour of chatting to GPT3.5 costs me $0.02

Would be curious what you mean by integrating the backend-api?

We are spending about 60% less. Workload has actually lessened since AWS is so much more stable. Getting to a similar DX as Heroku was quite the lift, but once it's done, it's done. These days we generally only have outages when we screw something up ourselves. I recommend https://github.com/aws/copilot-cli for starting out on ECS.

If you're still running on Heroku after everything that went down last year, you really have no one to blame! We are happily on AWS now.

At my current job (sr. eng) I have an average of 45 minutes of meetings per day

A few issues I have with this blog post:

1. It doesn't show off the unique capabilities of firecracker very well.

2. The comparison not very fair.

2a. The docker-build step (which dominates the runtime) is run without any caching, just by adding 2 lines to your build-push-action, "cache-from: type=gha, cache-to: type=gha,mode=max" you can make it a lot faster.

2b. ~1m20s of the time is just "VM start". GitHub Actions has had a rough time recently, but you should never wait that long to get your CI running in day-to-day operation.

2c. The tests are unrealistically short at 20s which allows the author to get to their 10x faster number.

Let's say the GitHub Action starts in 5 seconds, the GitHub Actions cache reduces the build time to 2 minutes and the tests take 10 minutes to run. Now Firecracker is 20% faster ...

You can also get comparable performance out of https://buildkite.com/ which lets you self-host runners on AWS meaning you're almost guaranteed to get a hot docker cache (running against locally attached SSDs). You can now start running your tests (almost) as fast with much more mature tooling.

Thank you for the reply!

I'm currently waiting for my EAD (Applied for a GC via marriage to a citizen). What's your opinion on expedite requests with the reason being financial loss (I have a pending job offer from startup)? Is it worth trying?

In those instances, do the managers at BiggerCorp who initiate the deal get the equity or the company?

Something I've noticed as well. Might be related to geographic diversification, or that "[App] for [Emerging Market]" better answers the "Why now?" question.

Incorporate a LLC and put the whole period as "Founder, XYZ Widgets LLC"

In which areas does Carvana own all the cars for sale?

While depending on a live DB for testing isn't great, why not just blow away database state after every test by running TRUNCATE / DELETE against all tables? DELETE especially is very fast (couple ms) if you're not inserting large amounts of data during your test runs.

maybe not with CDNJS, but perhaps you don't want every website to know you have AshleyMadison.com assets cached.

That is really quite crazy that a legally required event to discuss finances would prominently feature Tesla legal & finance. I think you might be onto something.

What the hell are you talking about? Tesla is Tesla because of their incredible engineering talent. The rest they do to amplify their car building efforts. If you offered Elon 100 incredible engineers/lawyers/financiers, he'll take the engineers every time.

How many car startups that achieve wide distribution has America had in the past 100 years?