alina 🌸🦴

alina 🌸🦴

@tei.pet

early 20s, it/she, aroace audhd bpdemon, puppygirl that meows may or may not be obsessed with javascript too much opinions are my own

533 followers504 following1.8K posts

i got one shot by fable so bad coming back to opus feels like im babysitting a toddler now i wish they make it included in sub eventually and hopefully raise the limits i burned through 5x in like a day after burning though 70% of 20x in 1.5 days

an issue with unemployment is that once there's no longer an anxiety-inducing reason to get out of bed in the morning – i tend not to, causing me not to tackle personal projects either...

the days just collapse into one continuous mush, my sense of time is struggling. like wdym it's already been almost 3 weeks and i barely did anything

its funny to me how people are slowly realizing that bun is indeed a garbage runtime and that maybe the unix people were onto something when they said "do one thing and do it well"

like, a ~week ago it successfully did an arguably harder version of the task (it had to work around some limitations in a library it was using) with very little supervision now im trying to get it to do the same task *without* needing to work around the limitations, and it's STRUGGLING 😭

did they silently reduce the reasoning budgets or something? the only plausible explanation i can think of, apart from running quanitized models during peak hours (but that would probably be visible on perf tracker so idk)

one sad thing about llms is that building silly stuff for fun is just.. no longer fun theres no longer any point in doing silly shit just for the sake of it (and maybe to show off a bit), bc most frontier llms would just oneshot it. and everyone knows that and would just assume you vibecoded it. :c

View full thread

on one hand yeah, leaning heavily into llm-assisted coding did help me overcome procrastination on some older projects i kept postponing. yet at the same time.. not actually seeing the finishing line may have been what kept me engaged? the result doesnt matter if i had fun or smth

i keep finding myself in a place where i just rly dont know what to do everything feels kinda boring and pointless when i can just prompt an llm and it will build a kinda shitty but still mostly working version of whatever i was gonna do, in a fraction of time and idk how to spend the time i saved

one sad thing about llms is that building silly stuff for fun is just.. no longer fun theres no longer any point in doing silly shit just for the sake of it (and maybe to show off a bit), bc most frontier llms would just oneshot it. and everyone knows that and would just assume you vibecoded it. :c

llms skew "is it worth building it" in more than one way. most of the discourse ive seen focuses on the "building stuff is easier than ever, so we build too much, even what we shouldn't" but for me the experience is kinda the opposite - if it's easy to build, why bother doing anything at all?

codex is weird. it might be a *bit* better a the "make X work" kind of tasks and one-shots stuff more often, but the code it generates is fucking awful and i find myself spending a lot more time cleaning up after it than after claude and it also seems worse at the "debug X" kind of tasks

biome fixes literally zero prettier's problems, you *dont need* to keep this shit in one line just because it fits the 120 line width, just let me fucking split it manually and dont revert it ffs

damn if only there was a deterministic and fast tool to move files while updating imports and we didn't need to dispatch subagents to do that like genuinely why dont they just expose vscode lsp to cc in its entirety. (ik that it has some own lsp thing but i cant get it to work 😭)

it feels like they reduced the 100$ claude max limits significantly. i never hit above 50-60% previously, even when working in parallel on multiple projects at once now it's almost at 75% after like 2 hours of very moderate work...

it feels like they reduced the 100$ claude max limits significantly. i never hit above 50-60% previously, even when working in parallel on multiple projects at once now it's almost at 75% after like 2 hours of very moderate work...

kinda checks out with their recent compute struggle tho... i really hope its temporary and they'll figure something out, i can't see myself paying even more than what i already am

got around trying sonnet4.6 in a real task and uhh its dumb. like really really dumb. it just. gets lost or something. and slow. working with it feels like an overconfident and overly eager junior dev. and its *really* bad at following rules from CLAUDEmd. bweh

i mean like, it fetched the reference source code three times in a row, but it wasn't enough apparently and it went to use grep.app mcp, failed bc of an overly complex query, fetched the same file a few more times, dispatched a subagent to fetch the fucking file. like lol.

watched cosmic princess kaguya first of all, those are illegal amounts of gay second of all, i want to be a gay virtual anime girl too!!! 😭😭😭

i kinda really like the prince+autistic girl trope in anime (won't tell the names bc it's technically spoilers but this is the second one i see and im sure there's more) <s>lowk makes me a bit more straight</s>