If I sell software to my customers that reduces their operational complexity by me investing some code, then I don't consider it a loss.
806 karma · joined October 18, 2011
If I sell software to my customers that reduces their operational complexity by me investing some code, then I don't consider it a loss.
https://se-radio.net/2008/03/episode-88-the-singularity-rese...
Super interesting approach. I see this eventually be integrated into future mainstream languages, though that may take a while. I suspect that the game programming crowd will try to use it first, due to the possibility to prove certain edge cases at compile time and skip the runtime cost. But perhaps this optimization drive is no longer the case because we've got bazillions of cores nowadays. I may be too old for these predictions. Cool nonetheless.
Refactoring code to reduce the number of lines is _compression_, akin to RLE coding.
Refactoring the code to lift conceptually coherent parts is _abstraction_.
Less compression, more abstraction. Then you're fine.
edit: ah, yes also a broker controlled component manager that can start, stop, monitor services over the mentioned broker. This is the carpet that brings the room together.
The harder problem is to enter Germany, but as you have EU citizenship, that's not a problem for you.
The more effort I spend on planning architecture with the AI, the less runtime bugs I need to investigate after it did the implementation.
This is definitely an agent problem instead of an LLM problem. Anybody got something explorative like this working?
You can't figure this out instantly except when you'd review everything the LLM produces, which I am not. So the round trip time is pretty long, but I can trace it back to the intent now because I commit every architecture decision in an ADRs, which I pour most of my energy into. These are part of the repo.
Using these ADRs helped a lot because most of the assumptions of the LLM get surfaced early on, and you restrict the implementation leeway.
I figured out some patterns in the way it behaves and could put more guard-rails in place so they hopefully won't bite me in the future (spelled out decision trees with specific triggers, standing orders, etc.), but some I can't categorize right now.
After 5 hours or so of doing this planning, I'm EXHAUSTED. I never was exhausted in this manner from programming alone. Am I learning something new? Feels like management. :)
Get the facts straight.
Not all implementations are re-implementations, so this approach won't work for everything. But for a new implementation in a new programming language than the original implementation, it works great. Built myself a MIB compiler, checked against smidump. Now it is more correct than the original, because smidump still crashes on some inputs, while mine does not.
So the news is not so much that Anthropic built a C compiler, but HOW.
Russia on the other hand is shit at waging their war in Ukraine but they achieved their objectives (land bridge to Sevastopol, etc.).
So the worry is not that Russia will wage a well fought war, but some war at all, even if they are shit at it, because it will do extensive damage either way. And we know for a fact that they don't shy away from it.