Thank you for reading my comment. I’m on the train headed to work and I’ll try to answer completely. I love talking about this stuff.

Do you believe that providing all that context, describing the existing patterns, creating an implementation plan, etc, allows the AI to both write better code and faster than if you just did it yourself?

For my work, absolutely. My work is a lot of tickets that were setup from multiple stories and multiple epics. It would be like asking me if I am really framing a house faster with a nail gun and compressor. If I were just hanging up a picture or a few pictures in the hallway, it’s probably faster to use a hammer than to set up the compressor and nail gun, plus cleanup.

However, a lot of that documentation already exists by the time it gets to me. All of the Design Documents and Product Requirement Documents have already been formed, discussed, and approved by our architecture team and team leads. Imagine if you already had this documentation for the asteroid game; how much better do you think your LLM would do? Maybe this is the benefit of using LLMs for development at an established company. Btw, a lot of those Documents were also created with the assistance of AI by the Product Team, Architects, and Principle/Staff/Leads anyway.

how much twiddling of your existing codebase do you need to do before an AI can understand the business context of it?

With the help of our existing documents and codebase(s) I feel I dont have any issues with the model knowing what we’re doing. I do have to set up my own context for how I want it to be done. To me this is like explaining to a Junior Engineer what I need them to help me with. If you’re familiar with “Know when to Direct, when to Delegate, or when to Develop” I would say it lands in between Direct and Delegate. I have markdown files with my rules and guidelines and provide that as context. I use Augment Code which is pretty good with codebase context.

write an Asteroids clone using JavaScript and HTML 5 Canvas

I would try “Let’s plan out the steps needed to write an Asteroids game using JavaScript and HTML 5. Identify and explain each step of the development plan. The game must build with no errors, be playable, and pass all tests. Do not wrote code at this time until our plan is approved” Then once it comes back with the initial steps, I would guide it further if needed. Finally I would approve the plan and tell it to execute while tracking it’s steps (Augment Code uses a task log).

Are you running your models locally, or do you have some cloud service? If you give your entire codebase to a 3rd party as context, how much of your company’s secret sauce have you disclosed?

We are required to use the frontier models that my employer has contracts with and are forbidden from using local models. In our enterprise contracts we have negotiated for no training on our data. I imagine we pay for that. I’m not involved in that level of interaction on the accounts.

How much pen-testing time are you spending on this code, error handling, edge cases, race conditions, data sanitation? An experienced dev understands these things innately, having fixed these kinds of issues in the past and knows the anti-patterns and how to avoid them. In all seriousness, I think this is going to be the thing that actually kills AI vibe coding, but it won’t be fast enough. There will be tons of new exploits in what used to be solidly safe places.

We have other teams that handle a lot of these tasks. These teams are also using AI tools to get the job done. In addition, we have static testing tools on our repo like CodeRabbit and another one I can’t remember the name of that looks specifically for security concerns. It will comment on the PR directly and our merge would be blocked until handled. Code coverage for testing is at 85% or it blocks the merge and we have a full QA department of Analysts and SDETs to QA. In addition to that we still have human approvals required (2 devs + Sr+). All of these people involved are still using AI tools to help them in each step.

I hope that answers your questions and gives you some insight into how I’ve found success in my experience with it. I will say that on my personal projects I don’t go this far with process and I don’t experience the same AI output that I do at work.

These types of articles always fail to mention how well trained the developers were on techniques and tools. In my experience that makes a big difference.

My employer mandates we use AI and provides us with any model, IDE, service we ask for. But where it falls short is providing training or direction on ways to use it. Most developers seem to go for results prompting and get a terrible experience.

I on the other hand provide a lot of context through documents and various mcp tooling, I talk about the existing patterns in the codebase and provide sources to other repositories as examples, then we come up with an implementation plan and execute on it with a task log to stay on track. I spend very little time fixing bad code because I spent the setup time nailing down context.

So if a developer is just prompting “Do XYZ”. It’s no wonder they’re spending more time untangling a random mess.

Another aspect is that everyone seems to always be working under the gun and they just don’t have the time to figure out all the best practices and techniques on their own.

I think this should be considered when we hear things like this.

Disneyland. Client needed a data migration. I’ve also had to do similar tasks by pulling over at rest stops because everything is always an emergency.

The one that happens to me the most is on Instagram. When there is overflow text on the caption of a post and it provides the “more” link, I accidentally hit the “save” bookmark icon because of how close they are. It’s usually some news post or something that I definitely have no interest in saving. It feels like bad UX design to me.

I remember when wireless earbuds first came out. The sentiment was the same “You’ll never see me with those because I’ll look like a crazy person talking to themselves.” Now it’s completely normal and society accepts it.

That only works if you masterbate while watching porn.

Ah I see. I wasn’t sure what they could/would be monitoring. I still don’t understand how they would block it if the computer is only connected by ethernet.

What kind of travel router were they able to block if you were connected to it over ethernet? I would think connecting by ethernet to a travel router that connects to a wireless router as a repeater would work.

The reality is that you had access to reliable internet, but they would only allow certain types of reliable internet. So you would need to communicate what your options were and work with them, or chalk it up to being an incompatible match at this point.

It doesn’t sound like the shelter staff is at fault if they’re just following procedures. Perhaps showing them an offer letter would have made them feel comfortable in allowing it for a little while longer.

I hope you keep trying and find a good match. I wish you the best of luck!

Boost dev was how I even found out about lemmy. So I actually followed the app.

I end up having this conversation often because I believe the Congress Apportionment Act is where we really went off the rails. With our technology, I believe we could handle 1600 representatives and they wouldn’t need to be full-time careers. Would congress ever agree to repeal the act?

It’s like when you cancel your Netflix when money is tight and then resub once you can afford it again.

We are just labor subscriptions for corporations.

Unfortunately, there are many plastic toothbrushes that are lasting lifetimes in our landfills. Once I learned that, I switched to eco-friendly ones. There just isn’t a need for a smart/ai toothbrush, IMO.

Mine has been programming, world history, and how to. They’ve figured me out.

Guy was originally gender neutral as it was used to call someone stupidly bold (iirc). The term was most often used toward a single gender that was known for being stupidly bold and became synonymous with that gender. That’s how it became gendered.

Sounds like Will Arnett’s Murderville