139 karma · joined March 9, 2021
"Dear visitor, Thank you for your interest in our organization. From our belief we keep Sunday as a day of rest in honor of our Creator. For this reason, all our business activities are shut down on Sundays. We hope for your understanding and are happy to welcome you on our site or in our showrooms on the other days of the week."
I'm average looking, she has a beautiful face and has been dancing since the age of 4. I'd have 0 chance with these kind of girls on dating apps. Absolutely 0.
Another good thing, that time social media have not yet screwed up people's self esteem and that helped a lot -> she has not overrated herself, I have not underrated myself.
We've been dating in person for a couple of billion years, we are hard-wired for that as body language tells a lot more in a fraction of a second than any made up profile text and over edited photos.
I was free to use whatever I wanted to build apps. One of these makes over £150k annually, another one is has 700+ internal users.
My tech stack and process was the following: -Python-Flask backend -Object oriented plain vanilla JS frontend with Redux state management (yes, it works without React) -MySQL db -Docker -Good enough documentation to be able to hand it over at any point of time if necessary -Test cases for critical things -Deployed everything to an on-premise server with using WinSCP
I really enjoyed the whole process as I only had to focus on the actual business problem and very actively worked together with the stake holders. The results: bug free apps that I rarely have to touch; great satisfaction and feedback from both clients and internal users; short product to "market" time.
Recently I joined the company's dev team. Mate, it's hell. We have to use React for even an app that has a login page, upload page and report page. The db is Snowflake that makes everything freakin' slow. We have mindlessly have to follow the company guidelines to pass all the "cloud gates" before we can go live. We have to pass Snyk, Sonarqube, use Azure Dev Ops, dev-qa-prod environment, 80% test coverage, less than 3% code duplication (nobody cares if it screws up readability); use Jfrog and god knows what, there are 15 different criteria that we have to pass.
The result: extremely sluggish development; slow application; the whole thing can break at 10 times more places; and it does break; the process seems more important than the actual app that we are building; user satisfaction is awful; no time for running experiments or deeply explore the problem.
We add such a complexity to so tiny apps that I could build over 1-2 weekends that it suffocates the application itself.
I'm looking for the way out, I'm sure there are better places but I'm really thinking about setting up my own company where I could use more common sense. If it's a large app then let's follow a strict process but when it's almost like a toy project then let's keep it simple and only invest in sensible amount of energy.
I've seen here the post about John Carmack notes what he accomplished on a single day, I have never got close to that but I was so productive, adding multiple features on a single day and that made me so satisfied. And now it's all about the "gates".
(They have backend courses as well)
Also, we have not implemented it, we can have one or multiple level of managers just like at a company and each would delegate a task to a worker (who could also be a manager) and they would report back the result. Just like in real life, a manager doesn't have to know how something is done, it should only know it's done and the get the results.
We work for a large company and very likely have 100s of apps. We could build wrappers around them e.g. using selenium and we could interact with even old apps.
We could also do the same approach with databases. The db itself would have docs, each table and each field as well. So we could ask ChatGPT to query data from the db and it could fully understand the data before writing the sql query.
Briefly: we tell ChatGPT what API based tools we have, explaines them in 1 sentence and where it can reach their documentation. We added documentations as endpoint. example.com/docs/main is always the starting point that returns high level overview of the app and all available endpoints to call. Every endpoint has its own documentation as well. E.g.: /geocoder has /docs/geocoder documentation endpoint that describes what it does, what input it expects and what it will return.
We also provieded ChatGPT with actions like read_docs, call_endpoint and end_conversation. An action is a structured JSON object with a set of parameters. If ChatGPT wants to interact with the mentioned resources, it emits an action, it gets executed and the answer fed back to it.
With this I can do a task like: "Get a 30 minutes drivetime polygon around 15 Bond Street, London and send it to Foster."
It plans and executes the following all alone. First it calls the geocoder to get the coordinates for the isochrone endpoint, then gets the isochrone by calling the isochrone endpoint and saves it, calls Microsoft Graph API and queries my top 50 connections to find out who Foster is and calls the MS Graph API's send mail endpoint to send the email with attachment to Foster.
It can hierarchically explore the available resources so we don't need a huge context window and we don't have to train the model either. Also we could implement multiple agents. 1 would be a manager and there could me multiple agents to perform each task and return the results to the manager. It would furthet reduce reduce the required context window.
Very likely some BS app will win the Hackathon like always like a market price predictor using Weka's multilayer perceptron with default settings but we believe our solution could be extremely powerful.
We want to try this with my dad. He has tinnitus for around 5 years, it started after an ear infection.
It works the same way as the method in obobbobo's comment.
It's FDA approved!
I don't think it's UTF-8 as Windows has been able to handle non-English alphabet letters for ages. I don't not know whether it has any specific, location related reason. I can work a lot faster with it than with File Explorer.
It's like the Bud Spencer and Terence Hill movies. They are extremely popular here, in Germany, Austria, Italy but the rest of the world have not even heard about them. https://trends.google.com/trends/explore?date=all&q=%2Fm%2F0...
We even have a statue of him at a frequented area. https://en.wikipedia.org/wiki/Bud_Spencer
https://trends.google.com/trends/explore?date=now%201-d&q=%2...
It uses Chrome's speech to text API (webspeechapi) for input, then it sends it to ChatGPT 3.5 and I use Google's text to speech API to generate audio response along with the text. So practically I can talk to ChatGPT.
I also want to add a dictionary module where I can generate and add example sentences and images to a words and phrases.
I'm sure there are complete teams working on apps like this as it's such a straightforward use case.
You can try it, it's all Hungarian but you can translate the page. https://convo.hu/ Invite code: CONVO