codebolt

The correct thing to do in this scenario is to create a new random login alias on your Microsoft account, make it the primary login alias, and disable login for the all other e-mails tied to the account.

I'm skeptical of letting agents run free like this. Even Opus makes decisions I don't always agree with. And I quickly lose my mental model of how the code is evolving.

I get more enjoyment and better results when the coding process is me and the agent working through a plan, at each step sparring over what to do next and how. Then I also catch the bad decisions before they manifest in the code.

Using Mistral or more SOTA models?

China has cheap coal powered electricity and leaders that make things happen. Europe has beaureaucrats that only love talking, high taxes and expensive energy.

Same here. Step 1 is usually a research doc where I simply describe the task and tell it to research the relevant parts of the codebase. This gets refined to a high-level plan, which gets distilled to a detailed step-by-step implementation plan.

When it comes to the actual implementation I prefer to work through it in small steps, where the AI explains to me exactly what it's about to do and why (and I approve) along the way. This enables me to catch it if it's about to do something I disagree with beforehand. And reduces the time I need to spend reviewing in the end.

My agentic workflow probably differs somewhat from the majority of others here, but I can positively guarantee you that both the quality and quantity of my output is significantly higher than it has ever been, in my 20-something years of writing code. And at least 90÷ of the code I've written this year was output by an LLM. You can keep sticking your head in the sand, in the end it will only be to your own detriment.

I'm with you all the way here. I derive zero pleasure from simply typing out the code once the spec is clear. Having a fast forward button to skip that phase is a pure win in my book.

I'd call that irresponsible use. One of the principles I try to stick by is to never offload any major decisionmaking to the LLM without oversight. Because some percentage of the decisions it makes are going to be wrongful (and more often just against my taste).

Not what I do. I'll reformulate the ticket description so that the purpose and as many details as possible about the solution are made clear from the start. Then I tell Opus to go and research the relevant parts of the codebase and what needs to be done, and write its findings to a research.md file. Then I'll review that file, bring answers to any open questions and hash out more details if any parts seem fuzzy. When the research is sound I'll ask Opus to produce a plan.md document that lists all the changes that need to be made as actionable steps (possibly broken into phases). Then I'll let Sonnet execute the steps one by one and quickly review the changes as we go along.

Just out of curiosity, what type of systems are you working on? What type of features did you implement on your 100k LOC week?

There are many ways to use an LLM to generate a piece of software. I base most of my projects these days around sets of Markdown files where I use AI first to research, then plan and finally track the progress of implementation (which I do step-wise with the plan, always reviewing as I go along). If I was asked to provide documentation for my workflow those files would be it. My code is 99% generated, but I take care to ensure the LLM generates it in a way that I am happy with. I'd argue the result is often better than what I'd have managed on my own.

Anyone test it out for generating 2D art for games? Getting nano banana to generate consistent sprite sheets was seemingly impossible last time i tried a few months ago.

Debugging and local testing is the main remaining use case of IDEs. Especially so for mobile apps where you need to manage one or more emulators.

At some point I think I'd prefer to deploy my own model in Azure or AWS and simply bring the endpoint to the coding harness.

As a AI-aware software engineer currently creating systems that integrate with LLM provider APIs for my company- who also has no idea what an eval is or how a data scientist thinks about RAG. I honestly don't see what value a data scientist would bring to the table for my team. Maybe someone would care to enlighten me?

Your view of what is happening in the neural net of an LLM is too simplistic. They likely aren't subject to any constraints that humans aren't also in the regard you are describing. What I do know to be true is that they have internalised mechanisms for non-verbalised reasoning. I see proof of this every day when I use the frontier models at work.

Opus 4.6 has a 200k context limit in Copilot. Could be the issue.

There must be a mechanism to rate the person submitting the PR. Anyone that wants to submit code to a well-known repo would first need to build a demonstrable history of making high-quality contributions to lesser known projects. I'm not very familiar with the open source scene but I'd find it very surprising if such a mechanism was not already in place. Seems like an obvious solution to the problem of vibe coders submitting slop.

Just because somebody has a bunch of power tools doesn't mean I'd ask them to build my house.

The difference between having a non-technical person and someone who is capable of understanding the code being generated and the systems running it is immense, and will continue to be so over the foreseeable future.

It's easy to imagine but there's still a vast amount of innovation and development that has to happen before something like that becomes realistic. At that point the whole system of capitalism would need to be reconsidered. Not going to happen in the foreseeable future.

I use the restore checkpoint/fork conversation feature in GitHub Copilot heavily because of this. Most of the time it's better to just rewind than to salvage something that's gone off track.

Any given system will still need people around to steer the AI and ensure the thing gets built and maintained responsibly. I'm working on a small team of in-house devs at a financial company, and not worried about my future at all. As an IC I'm providing more value than ever, and the backlog of potential projects is still basically endless- why would anyone want to fire me?

One issue is that developers have been trained for the past few decades to look for solutions to problems online by just dumping a few relevant keywords into Google. But to get the most out of AI you should really be prompting as if you were writing a formal letter to the British throne explaining the background of your request. Basic English writing skills, and the ability to formulate your thoughts in a clear manner, have become essential skills for engineering (and something many developers simply lack).

Where are you encountering all this slop code? At my work we use LLMs heavily and I don't see this issue. Maybe I'm just lucky that my colleagues all have Uni degrees in CS and at least a few years experience.

That's why I'm very careful about how the context is constructed. I make sure all the relevant files are loaded with the prompt, including the project file so it can see the directory structure. Also keep a brief summary of the app functionality and architecture in the AGENTS.md file. For larger tasks, always request a plan and look through it before asking it to start writing code.

That's a fair point, my code is likely to have some warts that an experienced Android/Kotlin dev would wince at. All I know is that the app has a structure that makes an overall sense to me, with my 15+ years of experience as a professional developer and working with many large codebases.

People aren't prompting LLMs to write good, maintainable code though.

Then they're not using the tools correctly. LLMs are capable of producing good clean code, but they need to be carefully instructed as to how.

I recently used Gemini to build my first Android app, and I have zero experience with Kotlin or most of the libraries (but I have done many years of enterprise Java in my career). When I started I first had a long discussion with the AI about how we should set up dependency injection, Material3 UI components, model-view architecture, Firebase, logging, etc and made a big Markdown file with a detailed architecture description. Then I let the agent mode implement the plan over several steps and with a lot of tweaking along the way. I've been quite happy with the result, the app works like a charm and the code is neatly structured and easy to jump into whenever I need to make changes. Finishing a project like this in a couple of dozen hours (especially being a complete newbie to the stack) simply would not have been possible 2-3 years ago.

MS Copilot for Android has some annoying UI bugs which they seemingly refuse to fix. The biggest is that the chat area sometimes gets randomly resized so that you can hardly read anything. There is also no way to search past chats. For all the billions they are spending on AI, their chat interface seems inexplicably half-assed.

Going to need a citation on this one.