I work on an ancient codebase, C# and C++ code spanning over 3 major repos and 5 other minor ones. I'm senior engineer and tech lead of my team, but I also do a lot of actual coding and code reviews. It's a somewhat critical internal infra.
I'm intimately familiar with most of the code.
I've become somewhat addicted to using coding agents, in the sense I've felt I can finally realize a lot of fantasies about code cleanup and modernization I've had during the decade, and also fulfill user requests, without spending a lot of time writing code and debugging. During the last few months I've been spending my weekends prompting and learning the ropes. I've been using GPT 5.x and GPT 4 before that.
I've tried both giving it big cleanup tasks, and big design tasks. It was ok but mentally very exhausting, especially as it tends to stick to my original prompt which included a lot of known unknowns, even after I told it I've settled on a design decision, and then I have to go over its generated code line-by-line and verify that earlier decisions I had already rejected aren't slipping into the code again. In some instances I've had to tell it again and again that the code it's working on is greenfield and no backwards compatibility should be kept. In other instances I had to tell it that it shouldn't touch public API.
Also, a lot of things which I take for granted aren't done, such as writing detailed comments above each piece of code that is due to a design constraint or an obscure legacy reason. Even though I explicitly prompt it to do so.
Hand-holding it is a chore. It's like coaching a junior dev. This is on top of me having 4 actual real-life junior devs sending me PRs to review each week. It's mentally exhausting. At least I know it won't take offense when I'm belittling its overly complicated code and bad design decision (which I NEVER do when reviewing PRs for the actual junior devs, so in this sense I get something to throw my aggression against).
I have tried using it to make 3 big tasks in the last 5 months. I have shelved the first one (modernizing an ancient codebase written more than 20 years ago), as it still doesn't work even after spending ~week on it, and I can't spare any more time. The second one (getting another huge C# codebase to stop rebuilding the world on every compilation) seemed promising and in fact did work, but I ended up shelving it after discovering its solution broke auto-complete in Visual Studio. A MS bug, but still.
The 3rd big task is actually a user-facing one, involving a new file format, a managed reader and a backend writer. I gave it a more-or-less detailed design document. It went pretty ok, especially after I've made the jump to GPT 5.2 and now 5.4. Both of them still tended to hallunicate too much when the code size passed a certain threshold.
I don't use it for bug fixing or small features, since it requires a lot of explaining, and not worth it. Our system has a ton of legacy requirement and backwards compatibility guarantees that would take many days to specify properly.
I've become disillusioned last week. It's all for the best. Now that my addiction has lessened maybe I can have my weekends back.
I've been using Perplexity for small, fast queries almost exclusively for the last year or so. Their Sonar model is Llama running on top of a Cerebras chip, and searches the internet in an incredible speed. Its results are astonishingly good (for a Llama model), although in more niche areas it still makes mistakes, so in those areas I usually double-check its sources or do an extra ddg search myself.
Actually I've never used chat gpt, I went straight to Perplexity after having discovered it. Their free tier is extremely generous (not even requiring an account). Not affiliated.
OP currently doesn't look it will affect that, seems like Open AI touts it for agentic coding only, not as an alternative to chat gpt, although that will probably change.
There's also bflat [0]. Not an official Microsoft product, more of a passion project of a specific employee.
"C# as you know it but with Go-inspired tooling that produces small, selfcontained, and native executables out of the box." Really impressive. Self contained and small build system.
Just wanted to say I enjoyed your post very much. Thank you for writing it. I love D but unfortunately I haven't touched it for several years. I also have some experience writing parsers and implementing protocols.
reply