A mix of gpt-5.5 and claude opus 4.7, wrapped in my own mobile web UI that doubles as planning software and document editor.
The reason for the mobile focus is I've been trying to detach from my home office as much as possible, meaning I do a lot of up-front planning via ADRs and task/story writing, then I spawn agents to actually work on coding tasks. The only part that really requires sitting at a desk is code review, manual testing, and deeper human-in-the-loop coding or debugging sessions.
If you are able to max out the $100/mo plans from either OpenAI or Anthropic, then that is already a very cost-effective option.
idk man the doner kebab I had in Berlin was way better than in Istanbul. Istanbul still had excellent food, just not the kebab for whatever reason. Maybe we just didn't try the right place.
Most of these takes seem pretty agreeable to me. I would push back on the premise a bit in specific cases, like when you have a manager that always seems to want something new and changes their mind all the time. You need to insulate yourself from that stream of wasteful work by just not doing it until it's obviously necessary.
speed alone doesn’t make someone a good programmer
OP didn't make that claim. They said all else being equal fast is better than slow. They also said that in their experience, the best programmers they knew were good because they were fast (not withholding other potential reasons they were good).
Real history that explains how existing power structures came to exist. Not the bullshit history that schools teach, which is just wrote memorization and usually ignorant of the most important themes of class struggle.
A mix of gpt-5.5 and claude opus 4.7, wrapped in my own mobile web UI that doubles as planning software and document editor.
The reason for the mobile focus is I've been trying to detach from my home office as much as possible, meaning I do a lot of up-front planning via ADRs and task/story writing, then I spawn agents to actually work on coding tasks. The only part that really requires sitting at a desk is code review, manual testing, and deeper human-in-the-loop coding or debugging sessions.
If you are able to max out the $100/mo plans from either OpenAI or Anthropic, then that is already a very cost-effective option.