Similar. I regularly use Github copilot (with claude models sometimes) and it works amazingly. But I see some who struggle with them. I have sort of learned to talk to it, understand what it is generating, and routinely use to generate fixes, whole features, etc. much much faster than I could before.
I’ve found copilot to generate worse code, and the editor integrations to be unusable (lets insert this block of code at the wrong place in the file for example), but overall for it to do the right thing enough that I can patch it. I’ve found Claude code just goes mad and gets stuck in a loop and I need to pull it out and figure out where in the hundreds of lines of code it’s generates in the last few minutes it’s gone so wrong.
I am a developer turned (reluctantly) into management. I still keep my hands in code and work w team on a handful of projects. We use GitHub copilot on a daily basis and it has become a great tool that has improved our speed and quality. I have 20+ years experience and see it as just another tool in the toolbox. Maybe I’m naive but I don’t feel threatened by it.
At least at my company the problem is the business hasn’t caught up. We can code faster but our stakeholders can’t decide what they want us to build faster. Or test faster or grasp new modalities llms make possible.
That’s where I want to go next: not just speeding up and increasing code quality but improving business analytics and reducing the amount of meetings I have to be in to get business problems understood and solved.
Similar story. I’m a bit younger, but Amiga BASIC/VB3/VB6/ASP/.NET was my path. There was a joy when “Visual Studio” meant “you can visually drag a component on and that is the app” instead of editing text files. But gradually we learned you need to be in the code. Sure you have figmas and low code tools today. But industry has gravitated back to editing curly brackets and markup in text files. And for good reasons I think.
I landed on GitHub Copilot. I now manage a team, but just last night snuck away to code some features. I find my experience and knowing how to review the output helps me adopt and know how much to prompt the agent for. Is software development changing? Absolutely. But it always has been. These tools help me get back to that first freedom I felt when I dragged a control onto a VB6 designer, but keep the benefits of code in text files. I can focus on feature, pay attention to UX detail, and pivot without taking hours.
I was just thinking about this today. Apples lack of any 3rd party integration for things like this and iMessage is really annoying sometimes. In addition to a secondary backup, I’d love to automatically sync some photos from a certain album to my parents photo frame. Or if I take a nice nature shot have it sync to a Samsung frame tv. I get the benefits of the walled garden but esp w photos and messaging it seems like opening up a little would allow for some innovation
I have used this in a “beta” feature for an enterprise app and really like it. In ~100 lines of code I have a secured OpenAI compatible endpoint that I can chat with, and write tools for in .NET. I have it doing natural language query over some data and it works quite well.
You can also expose the agents as MCP, AGUI and so it can be a tool you integrate with other AI platforms.
Kinda get what he’s saying: provide more metadata with structured logging as opposed to lots of string only logs. Ok, modern logging frameworks steer you towards that anyway. But as a counterpoint: often it can be hard to safely enrich logging like that. In the example they include subscription age, user info, etc. More than once I’ve seen logging code lookup metadata or assume it existed, only to cause perf issues or outright errors as expected data didn’t exist. Similar with sampling, it can be frustrating when the thing you need gets sampled out. In the end “it depends” on scenario, but I still find myself not logging enough or else logging too much
Fascinating llm use case I never really thought about til now. I’d love to converse with different eras and also do gap analysis with present time - what modern advances could have come earlier, happened differently etc.
As we are in the holiday season it may enlighten readers to know St Nicholas, from whom we derive Santa Claus, was known for two things: secretly giving gifts to the poor and needy, and slapping heretic Arius at this council.
There are many meme images of a phrase like "I came to give presents to children and punch heretics. And I'm all out of presents." on top of an icon of St. Nicholas.
I think AG UI is great if you are building the UI and the Agent at the same time and want a high bandwidth sync between them and the UI supports AG UI as an adaptor layer (they have done a lot of work making this easier for folks).
A2UI is most interesting for it's LLM generation options (not tools but structured output), it's remote message passing options (if you don't own the UI), and it's general-purpose-ness (same fairly simple standard which can work for many models, transports, and renderers).
They do fit nicely together. Sorry the naming conventions are complicated. There are 2 hard things in computer science: naming things, cache invalidation, off by one errors.
I really want this but for Azure Devops. If you're not familiar, Microsoft owns both Github and Azure Devops, and both do similar: git repos and project management. I can use Github Copilot, Claude Code CLI, etc. against code on my disk, including Azure Devops MCP. But what I can't easily do is like Github Copilot Agent and apparently this Claude Code on Web: Assign a ticket to @SomeAi and have a PR show up in a few minutes. Can't change to github for _reasons_.
Would love any suggestions if anyone in a similar story.
reply