When I was at a newish job (like 2 months?) my manager said I "speak more in a Brittish manner" than others. At the time I had been binge watching Top Gear for a couple weeks, so I guess I picked it up enough to be noticeable.
Of course I told him I'd been binging TG and we discovered a mutual love of cars. I think the Britishisms left my speech eventually, but that's not something I can figure out for myself!
Many of us just don't use JSON in our day jobs, weird I know, but true.
The only thing I use JQ for at work is parsing the copilot API response so I remember what the model names are - that's it! TBH, I could just skip it and read the json
If you really think this, `baby` is an apt name! Internet, Smartphones, and social media will all be more impactful than LLMs could possibly be... but hey, if you're like 18 y/o then sure, maybe LLMs is the biggest.
Also disagree with missing the train, these tools are so easy to use a monkey (not even a smart one like an ape, more like a Howler) can effectively use them. Add in that the tooling landscape is changing rapidly; ex: everyone loved Cursor, but now it's fallen behind and everyone loves Claude Code. There's some sense in waiting for this to calm down and become more open. (Why are users so OK with vendor lock-in??? It's bothersome)
The hard parts are running LLMs locally (what quant do I use? K/V quant? Tradeoffs? Llama.cpp or ollama or vllm? What model? How much context can I cram in my vram? What if I do CPU inference? Fine tuning? etc..) and creating/training them.
The FCC doesn't enforce very strongly, mudduck and others like him have been killing CB channel 6 (and sometimes 19) for like 2 decades and nothing has been done nor will be done.
I wonder if this can work with OpenCode (Claude Code fork which allows for other model providers: https://github.com/sst/opencode)?
I really don't like being tied to a particular provider or model, switching models has been really helpful to get past blocks and save money (especially with Deepseek!).
And, of course, I need to use Github Copilot's Open AI-compatile API at work...
Wild take lol, I was recently unemployed and once I started facing the very real possibility that I'd have to go work at the local sawmill (or UPS) for $20/hr I was willing to do almost any humiliation ritual these companies wanted... and be happy I at least had a shot instead of being ghosted again.
I support the fight against this kind of thing, but I also think it's entirely hopeless: They have all the power in this situation, and this is the future they're going to force on us.
> Wild take lol, I was recently unemployed and once I started facing the very real possibility that I'd have to go work at the local sawmill (or UPS) for $20/hr I was
My hot take is that if you're an unemployed software dev now, it could last over a year easily, and it's way better to spend that time actually working at the sawmill or UPS if you're lucky enough to get those jobs. Work on your skills and selectively apply in your off hours, spend conservatively, reduce expenses as much as possible. At the very least, it'll remind you to be humble.
Hyundai/Kia use a traditional 6-speed auto in their hybrids. I drive one, the engine stays at a few RPM stepping points during most driving (it likes ~1600RPM, ~2200RPM, and ~3600RPM). I had a Prius previously, and I like this different setup because it reduces "engine droning noise", which was terrible on the Prius.
Though H/K have recently introduced a new hybrid system with a CVT, so maybe 2026 or 27 model years will be different.
Since I'm only making one comment, I also want to say hybrid cars are better than ICE because there are fewer belt-driven accessories. Aircon in particular on an electric motor is a big improvement. Without the idling engine producing heat, hybrids are much nicer in hot stop-and-go conditions!
Also my Prius made it its whole life (200k miles and ~20 years) without ever changing the brake pads... amazing!
YUP! This is why I've settled on Aider and it's "IDE integration" (watches all files for comments that end in "AI!", which then invokes the AI). I can then use it with whatever editor I prefer. I view the vscode mono-culture as a bad thing. I also like I can use any AI backend I like, which is really how it should be: Vendor lock-in tools are bad, remember?
I guess you lose tab-completion suggestions, but I am not a fan of those compared to 'normal' tab-complete (if backed by an lang server). If I want AI, I'll write a short comment and invoke the tool explicitly.
EDIT: Of course, it really depends an your usecase. I maintain/upgrade C code libs and utils; I really cannot speak to what works best for your env! Webdev is truly a different world.
EDIT2: Can't leave this alone for some reason, the backend thing is a big deal. Switching between Claude/Gemini/Deekseek and even rando models like Qwen or Kimi is awesome, they can fill in each other's holes or unblock a model which is 'stuck'.
Folks don't want to hear it, but our careers are based more on luck than any of us would like.
I avoided the first big round of layoffs at my last company. How? By being so overwhelmingly awesome and valuable that they couldn't afford to lose me?? NO!
I agreed to a smaller pay increase that year so a team member could get a much-deserved larger raise. I accepted more stock grants to help make up the difference. The next round of layoffs was based on stock packages granted to employees. More stock granted == more better, right?
When I was at a newish job (like 2 months?) my manager said I "speak more in a Brittish manner" than others. At the time I had been binge watching Top Gear for a couple weeks, so I guess I picked it up enough to be noticeable.
Of course I told him I'd been binging TG and we discovered a mutual love of cars. I think the Britishisms left my speech eventually, but that's not something I can figure out for myself!