boardwaalk

Is anybody calling him Z or is this just laziness? It seems in bad taste anyways, given Russia is basically using Z as their swastika...

similar here: I tried Codex $20/mo on a trial and I ran out of 5hr usage mid way through a medium complexity task on a medium size model twice and gave up there. I don’t recall the equiv Claude plan being anything like that. Anecdata, but not great for OAI if they actually want to retain people on a trial.

I don’t know what people do with the open models but having tried a lot of them I just can’t make it make sense. they’re too dumb and it effectively makes them useless (to me). it’s probably worth being honest about the low ceiling here.

I do mean to be critical here. I wish there was better moderation so I could find more conversation about the actual discovery here. There are multiple threads on this and I keep scrolling and only seeing more conversation about the drama. Which is about the least interesting thing IMO. I suppose I’m whistling in the wind here and not helping the situation, but damn.

I let it go a few hours on a not trivial but well-known problem, and it felt like it was just a little too plodding and just kind of mucked around a little too much and wasn't aggressive enough about getting stuff done. I asked it to wind it down and finish up and it took another hour and 15 to actually stop and commit without really getting much more done. Not very impressed here, if you can't tell. This new version also seems like (maybe this is written somewhere, I don't care to look.) this cycles through compactions every ~250k tokens which, I guess, seems like it might save Anthropic money on KV cache but does net me anything be pretty frequent pauses. (It didn't seem to lose the thread, at least.)

Not gonna say I want 5.0 as an option still... but maybe I do.

Is there a reason to use this over something like Sunshine/Moonlight?

the problem I’ve found with these things is that models drift immediately. if it’s not a git commit hook that runs over docs and comments and commit messages objectively it’s probably useless. which I might try.

Claude is so friggin wordy and has no idea how place comments iff they actually matter.

Anecdotal, but putting in $10 and using it through codex, I blew through it in maybe 30 min to an hour of a light test drive and didn't get my little task done, which certainly didn't seem like any sort of token burning operation. I honestly wouldn't mind trying it more, but it didn't impress me enough to put more into it.

I also put $10 into DeepSeek when v4 came out and (checks) still have $6.30 in there and have gotten so much more use out of it.

I'm just hearing about this attack on Checkmarx.

We recently adopted it at work, and I find the thing to just produce garbage. I've never tuned out noise so quickly.

you have to appreciate the irony of a thing that's supposed to help protect you from vulnerabilities being one.

Those dependencies pretty quickly reveal themselves to be complicated and heavy. I wouldn’t blame Rust for that. I rarely need more than what workspaces and VCS based deps give me, but when I have, putting up and using a non-official registryis pretty easy.

How strange to come across someone whose medical stuff so mirrors my own. I was just a decade older and don’t have epilepsy symptoms with meds. I can get behind all the advice here. Running out of “juice” and needing a break is very much thing. Before too but more so now. And taking a lot of semi stream of consciousness notes to help my more limited memory is too.

I had one neighbor with the announcement thing but they eventually turned it off. No illusions that it’s not still recording. But how horribly hostile to have that on, right? No accounting for taste, I guess. I’ll continue staying off nextdoor and the rest and keeping my camera feeds to myself…

Or we’ll just leave them behind and that’s fine. And I work day maintaining old stuff of varying quality. Conceptually, software composting.

I agree. I think we can reasonably posit why given the source. Call it selective YIMBYism maybe?