hi
Claude Code Unpacked : A visual guide
461–464 of 464 posts
Re: Claude Code Unpacked : A visual guide
#462Earlier quoted context omitted.
LLMs read and write human-code because humans have been reading and writing human-code. The sample size of assembly problems is, in my estimate, too small for LLMs to efficiently read and write it for common use cases. I liken it to the problem of applying machine learning to hard video games (e.g. Starcraft). When trained to mimic human strategies, it can be extremely effective, but machine learning will not discove…
But starcraft training is not through mimicking human strategies - it was pure RL with a reward function shaped around winning, which allows it to emerge non-human and eventually super-human strategies (such as the worker oversaturation). The current training loop for coding is RL as well - so a departure from human coding patterns is not unexpected (even if departure from human coding structure is unexpected, as tha…
AlphaStar (2019) refined through self-play but was initially trained on human data. I don't know of any other high-level Starcraft AI, but if you do let me know.
Re: Claude Code Unpacked : A visual guide
#463A 500k line codebase for an agent CLI proves one thing: making a probabilistic LLM behave deterministically is a massive state-management nightmare. Right now, they're great for prompting simple sites/platforms but they break at large enterprise repos. If you don't have a rigid, external state machine governing the workflow, you have to brute-force reliability. That codebase bloat is likely 90% defensive programming;…
[dead]
Re: Claude Code Unpacked : A visual guide
#464Earlier quoted context omitted.
>> It would be insane to code anything by hand these days. I strongly disagree, but it made me chuckle a bit, thinking about labeling software as "handmade" or marketing software house as "artisanal".
There's a lot of errors you can miss by coding by hand, even as a seasoned developer. Try taking Claude Code, point it at your repo, and ask it to find bugs. I bet it will. Claude is actually a crazy good vuln researcher. If you use it that way, your code might just be more secure than written purely by hand.
[dead]