151–160 of 231 posts
Earlier quoted context omitted.
> A lot of code is being written and a lot of it is going to be a real future burden. This assumes that the models of the future won't find it easier to just throw the code away and rebuild it This also assumes that the same application build by humans wouldn't become a "spaghetti mess".
errors compound
> Out of ideas, I asked Claude how I could find it. It suggested tracking the Bluetooth signal strength, then wrote me a meter in about a minute. two sentence horror
Earlier quoted context omitted.
errors compound
...Whether you are an LLM or human. And, on average, LLMs write better code than humans. Not you, of course. You write exceptional code with zero errors that never needs rework. I'm talking about the rest of us.
i write pretty good code when i need or want to, yeah. sadly LLM code gives me a headache so the current psychosis standard has made work a bit painful.
the codebases are becoming LLM-first human-second so even if i wanted to be natty it's not really viable. might as well spend my employer's money.
Earlier quoted context omitted.
You can run 100mbps with only two pair, if you have something on at least one end which you can tell to only negotiate to 100.
This is true. But you can also run gigabit ethernet over a single pair (1000BASE-T1) often called SPE. The transceivers are more expansive than normal four pair gigabit and the official cable requirement is Cat6A but even if the headroom is lower it will work on lesser Cat levels.
Somehow, on HN, suggesting to use an LLM to solve some problem gives you negative responses. But then ... posting to HN that you've used an LLM to solve a problem is OK?
Earlier quoted context omitted.
People tend to not realize how far these models have become. I remember when they would always hallucinate APIs that wasn't there or make up fields that didn't exist.. those problems are virtually solved now. So with that in mind, why wouldn't AI be able to write better code? The code would have to be maintainable by AI itself (operating based on the assumption that the future will be Agentic Engineering)
I don't use Claude, but isn't the consensus right now that Opus 5 is worse than previous generations? I suppose you could just commit to always using Fable and never use Opus, but it > might decide your 8yo is actually trying to build a cleverly disguised bomb so her request gets silently downgraded to a dumber model My contention isn't that models haven't improved or won't keep improving – my position is that the bu…
sigh
Yesterday my 8yo prompted (using voice recognition) Claude to make a game where it would play her a song (say Twinkle) and she had to play it back and get scored. The UI was a nice piano with visual feedback. The laptop key served as the keys until I prompted for midi support so she could use the electric piano. The whole thing took about 15 minutes. Meanwhile, one peak at the code and you can already see the state s…
> A lot of code is being written and a lot of it is going to be a real future burden. This assumes that the models of the future won't find it easier to just throw the code away and rebuild it This also assumes that the same application build by humans wouldn't become a "spaghetti mess".
ed sp