Okay so now I think you're describing the behaviour I take for granted with the harness i.e. Claude Code.
Having good repo readiness through a good agents/claude.md file + tests + docs means the LLM is able to read more files into its context.
It never occurred to me that anyone would prompt in isolation of their repos but I guess thats exactly what it was like for me last year when I was just feeding ChatGPT prompts away from the repo.
Honestly im proud of the problems I'm able to solve today now that I can use AI to do it so quickly.
Even when I stop and manually check all the work the AI has done, it's still much faster and I'm having to rely on my knowledge and experience to do so. When I'm vibe coding I'm relying on that same knowledge and experience to architect the solution rather than deliver it.
Ive seen the other side- the colleagues who all of a sudden think theyre engineers and are unknowingly exposing critical commercial data to our competitors. That side is scary...and gives me hope that my role while changing, is far from dead.
Also I have hobbies - i only work to pay for them. If "the man" wants to pay me to spend tokens...fine by me. I'll be here to clean it up if it all goes wrong.
Ok so i think i do all of these things and would just describe them as "other ways to prompt and LLM" - i think the nuance youre shooting for here is that using these methods you are "pre-preparing" the prompt - not thinking about it at prompt-time and thus likely to miss stuff.
e.g. Feeding a TODO is just the same as copy-pasting that todo in as a prompt.
Have I understood you correctly?
I'm just trying to do my job in the system I'm in friend.
I know I'm gonna get flamed for this, but here goes.
I have vibe coded a system at work that has enabled me to deliver value in a fraction of the time I expected. My verification steps have been around whether it does the things I told it I wanted it to do. I'm not maintaining the syntax and I'm not expecting anyone else to. Ever.
That said, our teams that deliver products that touch customer data or financial records....they shouldnt (and dont) engineer this way. The tech isnt there (yet).
Let the flaming commence.
Tell me more? It's the only way I'm familiar with interacting with an LLM
I have to say I am sick of having to give a safety briefing to passengers when they get a ride.
"If we crash and burn, the manual release is behind there" points
Why didnt they just put regular bloody handles on!?
For me, that's not compelling. We all have different priorities.
If you're referring to their announcement last year about discontinuing meshnet, they've retracted that.
I know there are alternatives but why would I go to any effort to set them up when i have something that has worked exactly as I want it to for the last 2yrs? The cost of nordvpn is sufficiently low enough that I wouldn't switch to something just because it's free.
I've used NordVPN for a couple of years and never had reason to switch. None of it gets in my way, and it's just worked.
I'm sure others are just the same, but ive no reason to put in effort to change when I have a working solution.
Plus it's double effort cus I dont think anyone else does a meshnet alternative so I'd be setting up tailscale too.
Start at 1 and work your way up in increments of 1.
See you in about 100 years give or take a few decades.
Gotcha...I've always struggled to pick up the vocabulary around technical concepts - I guess ive just never prioritised it, and now this whole new field has materialised with a whole new vocabulary to go along with it! I get the tech. The words are my achilles heel.