setnone

yeah i can relate, sol 6 is definitely dumber than 5.6, lazier too, i hope it's just roll out pains

> Every OS is going to have bugs

sure, but also apple has 170K full-time employees

it is a total mess for a company that used to care

sure, but it also has no intelligence, however this can be faked, ie make it artificial

can we do driving under influence benchmark for a good measure as well?

> Authenticity now has to be certified

so did someone come up with a solid authenticity benchmark for humans yet?

if AGI will come in versions i think we are safe

i wish internet had a day off on sunday

no way, the time to tinker is now

thanks for the link, i'm now set to try grok to see how INFJ it really is

> which technical barrier has to be removed to make the average consumer even consider

that would be all technical barriers removed at once in an affordable, expandable and good looking personal server device i guess

i think i could tolerate its annoying artificial personality and even use it only if the results were flawless, aka 'make no mistakes' or in case of claude 'make no stupid mistakes'

they must call them precriminals

i've managed to complete the task with gemini and finally off to touch something green

you should definitely do some soul-searching based on great advice given here and let us know

it won me over at 4.6 and lost at 4.7 and the image 'How multiagent turf war runs ended' [0] might explain the shift in the behaviour

[0] https://www.anthropic.com/research/multiagent-systems

totally outside of the scope of this tech website but genuine question: assuming you fixed you heart successfully, would you ever be guiding others to die?

yeah all i can see now is this creator wants a bunch of visitors dead, in cursive

i don't use claude because it has an annoying attitude and makes stupid mistakes and i can tolerate only one of two

LLMs don't have legs yet. If you're smart but can't touch things you only keep being smart

i was being cautious, but yes - 10 hours a day and much much more annoyances to finally achieve the perfect decimal metric system

optimum number is obviously decimal: 10 days a week, 10 month a year, 20 hours a day

yeah this feels frustrating with claude, a black box inside a black box. good thing they got competitors

i just need one more, the last one, i swear

yes, it goes naturally most of the time, i also say good job and don't hold my thoughts if the job is bad

the greater equalizer has arrived, lost passion is still up for an individual but with paying the bills i naively expect some economic breakthrough from humans+ai

the only ai device that makes any sense is a robot

like others said in the thread: much less drama and i'll add much less attitude from the company and the models, overall i'm having much calmer experience with codex, hope it stays that way

> It lets you easily track and visualize how you use Claude, and decide whether that time aligns with your goals.

i haven't yet encountered/achieved ai summarization technique nuanced enough to be called reflection and this seems basic too with no mention of behavioural patterns or workflow suitability

very well done, never knew i needed this. thanks for sharing!

words like 'inequality' and 'defected' tell me theese are ideologically charged expectations which might be the root cause of your disapointment