Usually when something like that is proposed seriously it isn't supposed to start from the second home already, but a bit further as there's very little social benefit in excessively taxing a flat inherited from your grandma waiting for your children to grow up either.
The flux in flux core solder is completely useless for PCB soldering, It needs to already be on the PCB when the molten solder meets it because its main purpose is wetting the surfaces and reducing the surface tension of the solder so that it flows easier. Properly fluxed solder behaves very differently from the stubborn solder balls people normally experience when starting out.
I never interface with the peripheral in an ESP32 directly. I guess I really need to read the Free-RTOS code. Micropython just uses that, last I checked.
I had a similar approach, but in the end I don't think it's feasible to actually sufficiently follow the rule 2. It sounds good in theory, but in practice you'll always take some mental shortcuts that you may not even be aware of. Try digging into an unknown codebase to fix some issue and compare how much will stay in your head a week after if you do it yourself or if you "completely understand" what an agent did for you. When I do it myself, it contributes to my general knowledge and I mostly retain the important parts in my head even if I lose the details over time; when I try to own what an agent did as if it was mine, it feels like I understand it well at the time after putting some effort into it but then I forget it all very fast. Ultimately I decided that having an LLM help me there is actually detrimental to my goals most of the time, and that's without even considering some other concerns raised by sibling comments here such as time and business pressures.
Agentic harnesses go in the exact opposite direction to what I'd want to get from LLMs. I don't want another black box to (poorly) work on a black box for me, I want to be better at reaching into and understanding boxes that I already have in front of me. I don't want tools to autocompact contexts and store generated memories to facilitate long runs I have barely any control over, I want tools that allow me to painlessly craft a more relevant context for short ones. I don't want agents to author commits, I want them to use Git (or other tools) to get the information that I'm looking for when it's tedious to do it myself. I don't need them to do the fun and beneficial part of the job for me, I want them to do the boring parts that I already know how to do which block me from proceeding because my brain just isn't interested. Some of those things you can script yourself relatively easily, but the current tooling for LLM coding is absolutely atrocious and disconnected from programmer's needs.
The main output of my work is gaining a better mental model of systems I work with. That's what lets me grow and that's what makes people want to pay me rather than someone else to work on these things. Anything else, including the produced code itself, is secondary to that. In general I find it pretty hard, although not impossible, to use LLMs in a way that doesn't diminish my output, especially with this tooling that seems explicitly designed to make it hard. After all, reviewing things is so much harder than writing them yourself, and you can't feel accomplished by something you haven't done.
The people spreading fear about environmental collapse and claiming to be terrified of it, are displaying behaviors that contradict their claims. The people saying the ocean is rising and going to swallow communities while buying mansions on the coast and flying around in private jets, are either displaying extreme cognitive dissonance or aren't really that concerned with the environment collapsing. If it were one or two individuals displaying this behavior I'd blame cognitive dissonance, but it's pretty much every high-profile politician / celebrity.
reply