I feel like this is a great approach for LLM assisted programming because things like types, function signatures, pre/post conditions, etc. give more clarity and guidance to the LLM. The more constraints that the LLM has to operate under, the less likely it is to get off track and be inconsistent.

I've taken a shot at doing some little projects for fun with this style of programming in TypeScript and it works pretty well. The programs are written in layers with the domain design, types, schema, and function contracts being figured out first (optionally with some LLM help). Then the function implementations can be figured out towards the end.

It might be fun to try Effect-TS for ADTs + contracts + compile time type validation. It seems like that locks down a lot of the details so it might be good for LLMs. It's fun to play around with different techniques and see what works!

I'm exploring ways to integrate GitHub Copilot more effectively into my daily development work across different domains: web, backend, and mobile app development. My idea is to create a "prompt book" for each domain, containing common tasks and queries. This would allow me to quickly use Copilot to generate detailed code snippets based on a curated list of prompts tailored to the task at hand.

As an example Copilot for security has a prompt book pre-built by MS for security tasks: https://learn.microsoft.com/en-us/security-copilot/using-promptbooks

In the domain of backend programming this could help with:

  - stub code for endpoints
  - stub code for common file types
  - stub code for types of integration and unit testing
  - answer common questions like whether an API change is breaking
  - give tips on common logging and error handling cases

I'm curious to know if anyone in the community has experience creating or using prompt books with Copilot. Are there existing resources out there, or has anyone found this approach beneficial for their development workflow? Any insights, examples, or resources you could share would be greatly appreciated. :D

Comments URL: https://news.ycombinator.com/item?id=39688191

Points: 1

# Comments: 0

The best would be a TTS system at the level of OpenAI's but with voice selection like GCP TTS so you can get quality and a range of voices.

Copyright would probably spike any monetization effort but you could try. It would be nice to have an open source tool for this though! :)

It's the team that creates that kind of opportunity for feedback though. If the team has dysfunctions like rejecting deeper discussion or not working beyond jira tickets or checking out at meetings, etc. then it's not going to work. Someone that's good at that kind of supporting discussion will feel push back when fostering those discussions so it will fall off over time.

The teams that do the best work and are the most fun to be on can host those types of discussions though, even remotely. It's worth experiencing if you haven't!

What do you want to do with coding? What's going to give you the most leverage in the long term?

That course is going to dump you into the deep end for modern web dev. You'll probably struggle with it because it's taking on a bunch of things all at once. Some of the technology is also temporary. Will MongoDB or GraphQL still exist in 30 years? Will HTML, CSS, and JS exist in 30 years? Focus first on fundamentals that will give you a leg up.

I know professional frontend devs that still struggle with HTML because they went straight into React without learning semantic HTML first. If you can master the basics early on, then learning React and other frontend frameworks later becomes way easier.

Start with building web pages rather than web apps. You can do apps later but there's a lot more stuff going on. It's like trying to ride a unicycle while juggling flaming torches and balancing a spoon on your nose. Maybe you could sort of figure it out but it's better to split up the tasks and handle each in turn. That course is for people that already know the basics and want to try balancing on a new unicycle.

If you want ways to practice frontend, try building copycats of websites. Read the DOM, look stuff up, make lists of HTML elements or JS built-ins and memorize them. Play games to learn CSS flexbox or grid. Do whatever as long as you like it and it's teaching you the way.

There's lots of other stuff like frontend challenge sites that are good too. You'll always be "challenged" going forward for professional projects. Some might be really easy tasks, others will be hard. Get used to being resourceful and learning how to figure things out. It's an infinite game.

This style of learning isn't unique to frontend. If you wanted to be a backend dev, learning Spring Boot before design patterns, networking, etc. would probably be a bad idea. It's better to start as a beginner and embrace learning the basics. Go slow and master things step by step. Eventually it pays off.

You could also zoom out and abstract things to help with programming languages. Popular languages are pretty similar. Familiarize yourself with basic control flow syntax in one language and chances are it carries over into others. The same goes for "paradigms" like imperative, OO, and functional programming (others exist but they're more niche). Learning a paradigm is like rebuilding the thought process for your brain. If you learn different paradigms, then your thinking gets more flexible and you can approach problems differently. You might like the "aha" moments you get when things finally connect too!

I still have hope that frontend will eventually turn back to web components now that HTML templates, Custom Elements, Shadow DOM, and ES Modules are fully adopted. One of the problems is that this stack is foreign even to professional web devs that hail from React land. It's weird because it's native browser tech adopted by the W3C and painstakingly built into the browsers. Maybe it picks up after someone rewrites the react-dom internals to support web components and adds a new tooling layer over it?

It's not bad tech and web components are built into the platform of the web now so they're not really going anywhere...

psychology of intelligence analysis book link: https://www.cia.gov/static/9a5f1162fd0932c29bfed1c030edf4ae/...

previous discussion: https://news.ycombinator.com/item?id=14852250

Comments URL: https://news.ycombinator.com/item?id=36281945

Points: 64

# Comments: 45

I try to give as much context as possible. Stating goals and risks of the project. The more info you give it, the better it does at helping you. Around 500 words for an initial prompt gets good results.

Break down the project into parts and take on the most risky/uncertain part first.

As you work through the design, continue to refine the ChatGPT conversation by giving it more info. Keeping around 200 words is good. New articles can be summarized to get it up to speed on post 2021 info. Blog posts can also be chunked out and passed through to give it more info about the problem.

When the plan seems good enough, code through the steps to create the solution. Keeping things realistic and making some slow but steady progress is better than hammering it all out in a day. Discipline over passion.

I used it for a recent project and it completely exceeded my expectations. Not trying to hook onto the current AI bandwagon, it just brought me to solutions I would have never gotten to on my own.

The computer architecture is funky so it makes installing some distros a pain in the butt.

It was something like a 64-bit EFI bootloader for a 32-bit OS. The combo just doesn't work without compiling your own kernel. It's pretty uncommon. No biggie for someone that does C++ or embedded systems though.

Anyway, I'll shoot you an email with some pics and you can let me know what you think.

Work is supposed to be fun too. Some people get a rush from working on hard problems. There's at least some joy when you debug a heisenbug for a day or two and finally solve it or take on an impossible project and succeed. Having a team that you gel with where everyone is high flow state makes you look forward to doing work things too.

When you look at it economically as a 8 hours in $$$ out, you're looking at the short-term and discounting your long-term personal growth. If you aren't growing in your job, leave and find a place where you can build your skills and work on things that you find enjoyable.

There are probably some software jobs that would be fun to do. Why not go for a fun job doing something you love if you're currently stuck?

- laying out how I'm going to program before starting

- using TDD for most bug fixes and refactoring efforts

- learning how to steal the best parts of code from other people

- code reading everyday via PRs (my mental VM is pretty close to a real VM)

- learning algorithms and data structures (at least the basics, I'm no competitive programming pro)

- learning how to do code archaeology with git blame

Left to my own devices I would have done one or two sessions and then quit. Now I do two strength sessions per week and long walks one or two days per week. It's not a lot but I can feel the change. I might stick with it for 12 months but it costs a decent amount.

My trainer drives out to where I live and we do exercises using body weight and basic equipment (dumbbells and boxes). It also helps since I can make note of the exercises and copy the routine once I kick into my own training. They can give you lots of useful tips for how to build muscle and stick with it too!

I was treating it more like a course in how to stay in shape for the rest of my life. I'll probably do strength training and walks from here on out until I die of old age. (early 30s btw)

You can still be yourself and make the world a better place for others. Just because some people have problems doesn't mean you have to emulate their bad behavior. The golden rule still applies and lots of people are still looking out for each other. If you run into problems, get involved with your community to try to solve them.

Instead of focusing on all of the external problems around you, focus on how you're processing them. It's okay to get therapy if it seems like overload. It's also okay to just not do anything for a weekend so you can de-stress and relax.

Try tuning out from all of the noise for a little bit. There's probably some internet/news withdrawal at first but after you stop worrying about everything, it's easier to see what's directly affecting you.

Prioritize fun stuff like finding a good book and making some tea. Go hang out with friends and have an adventure. Be unproductive for a while. Do weird things. Take an art class or find a community group. Life is happier when you're in a positive community and having fun. Most people are still good.

Some of the big players have moves like that which work well given the right market conditions. My guess is that they have many, many patterns like that to trade on or models which are right more often than not. I don't know anything though since I'm a 101 retail investor... Positional options trading and volatility stuff makes my brain hurt :(

Have you seen strategies like that before? It's really interesting to dig into but seems to require a lot of knowledge to know how to trade on.

[0] https://en.wikipedia.org/wiki/Post%E2%80%93earnings-announce...

[1] Positional Options Trading: An Advanced Guide, pg. 90