Alexey Inkin | Flutter GDE
689 subscribers
29 photos
1 video
69 links
Download Telegram
A full-time personal assistant is wanted. Remote job from any country. Example tasks:
-- Find the top 20 awards in programming in the world, apply for a jury member.
-- Write and send personalized replies to Upwork jobs that meet given criteria.
-- Compose prompts and generate a 100 images with Midjourney for given concepts, choose the best images.
-- Based on my voice message, compose a job post for a programmer, pre-screen the candidates with given criteria.
-- Find a helper to form a legal entity in a country X.
-- Gather documents for a visa application to a country Y.
-- Find an apartment for rent in the city Z so that I only need to visit once and confirm.
-- Find a buyer for a used car by generating a stream of prospect buyers to someone who only needs to show it.

Requirements:
-- None of that scares you. On contrary, all of that is interesting for you.
-- Written English and Russian languages sufficient for business.

Schedule: flexible.

Pay: $600 / month.

#job #assistant
4😱1
How to make it to an interview for a personal assistant

I had 27 responses to my job post. Out of them:

- 7 (25%) had attached any resume.
- 2 (7%) had their resume formatted well.
- 6 (21%) had good grammar in the chat.
- 13 (46%) put all they had to say in a single message.
- 18 (64%) had their first name on the profile.
- 9 (32%) had their last name on the profile.
- 19 (68%) had a photo that could be them.
- 10 (35%) had a photo pleasing enough to do business.

Those points are critical because the clarity of communication is the number one skill for an assistant. A response to a job post is the first opportunity to show it.

I interviewed two of the candidates who scored well and gave both of them their first tasks. Of course, it was not solely relied on those points, but they are extremely important.

Noticeably, only one candidate has asked for the feedback after the rejection.

Follow the checklist, ask for feedback, and your chances will improve an order of magnitude.
👍1👎1
Wow, this comment from a Googler is worth a lot. Go ahead and read my article if you have not yet: https://medium.com/flutter-senior/avoiding-late-variables-in-dart-abdb4c2b57e7
🔥1👏1
Last week I had an idea of a side business. I launched a channel for Russians to learn English words through generated content: https://t.me/word_of_the_day_rus

This week I asked a few friends in, and now we have 55 followers there.

The plan for the next week is to:
1. Estimate the follower cost through ads.
2. See if I can put up some app with these materials.

It is odd to be a Flutter GDE without a single app in any of the stores. 🫢
This week:

1. Thanks to my friends and some paid ad, we are now at a hundred followers in the words channel. The follower cost is $1.2 so far.

2. I have purchased visualdict.com domain name for the dictionary (not working yet).

3. I put up a skeleton for the app.

Next week I plan to publish the web version of the app with whatever words we have in the channel (should be 29 by then).
400 followers on Medium!
Join if you haven't yet.

https://medium.com/@alexey.inkin
👍1
Working with ChatGPT on a dictionary is not easy. This is how it defines «the», the most frequent word in English.
Here is the alpha version: https://visualdict.com
It only has 5 words of the 29 from the channel because I need to automate publishing better.

Not that I want everyone to rush there. I just set the goal last week to publish, and making things public helps me keep up with the schedule.

Also I tried more ads in Telegram and got a few followers for 25 cents each which is below market value. Looks like the channel is interesting and my ad post is good. Or it could be luck, the data is insufficient.

Next week plan:

1. Load the top 200 English words, without images so far. This will make the dictionary useful for at least something like teaching kids the basics.

2. Automate generating pronunciation MP3s. The service I use for speech charges huge money for API but is cheap for normal UI usage. I want to try Selenium or ordinary JS to mass-produce those MP3s with the UI. This is also good for someone stuck in Flutter and never used Selenium in all strength.
2👏1
How ChatGPT stores the state of a conversation? Well, it does not. The model is stateless, and to get each response the chat app sends the entire previous conversation including the model's earlier responses.

I learned that while experimenting with it through the API, there we must manually send the history. This is the recommended community package for that: https://pub.dev/packages/dart_openai

This discovery was a relief. Seeing ChatGPT for the first time was frustrating as it showed how much ingenious stuff was out there I am not competent in. But this boils the problem down to the plain old "neural network with input and output". This is comforting.
Still working on the dictionary app. This week:

1. I have generated text for the Top 100 words, have not published yet.

2. I started the work on the editor UI. This is because the top words' definitions from ChatGPT require more proofreading than I anticipated. Word senses sometimes repeat or are just glitches. I will have to hire a proofreader. If we are going into thousands of words, the usability of the editor matters a lot. I have done ~60% of the editor. See the screenshot of editing the word "new".

Noteably, rare words mostly need no manual edits. Probably it's because ChatGPT learns them from dictionaries while it learns common words from all sorts of texts.

3. I put some ads and got some more followers at $0.25 each, now got 214 followers in the channel. Still hesitate to advertise more because I want the dictionary app to be ready before inviting people in.

Next week plan:

1. Complete the editor.

2. Hire a proofreader.

3. Publish the top 100 words without images.
The architecture of the dictionary is peculiar BTW. The source of truth for each word is a version-controlled JSON deployable to Firestore with Terraform. The Flutter app can switch between Firestore and local JSONs with a layer of abstraction I have developed about 2 years ago and published in packages.

This allows me to:
1. Version-control the dictionary data without dumps.
2. Work on any revision of data without environments and stands.
3. Review the work of proofreaders as PRs.
4. Reuse the app for the admin console.

Do you explore similar workflows? Would like to read more about mine with code examples? Let me know in the comments.
Still working on the dictionary. The week results:

1. The word editor is "complete enough" to not do anything until we publish a thousand words and see if we can get traction.

2. The proofreader is found but will only start next week.

3. Ads failed resulting in $1.2 per follower in the channel.

The plan for the next week is to publish the top 100 words and all 40+ rare words from the channel.
500 followers on Medium -- check.
https://medium.com/@alexey.inkin
🔥3
This week:

1. Created firestore_api_converter package.

2. Updated the dictionary web app: added the language switch, so definitions are available in English and Russian. Published the top 100 words + over 40 words from my "word of the day" channel.

Next week plan: No new coding, will write about my new packages. A new assistant will prepare and publish the words 101-200.