HackerLangs
TopNewTrendsCommentsPastAskShowJobs

setnone

260 karmajoined há 7 anos

Submissions

Ask HN: Is Codex with GPT 5.5 Extra High being dumbed down?

7 points·by setnone·há 11 dias·9 comments

Ask HN: What's your AI assisted dev setup that actually follows instructions?

1 points·by setnone·há 3 meses·0 comments

Ask HN: What recent thing you've been tasked improved your skills significantly?

3 points·by setnone·há 8 meses·0 comments

comments

setnone
·há 15 minutos·discuss
the only ai device that makes any sense is a robot
setnone
·ontem·discuss
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
setnone
·anteontem·discuss
> 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
setnone
·há 8 dias·discuss
very well done, never knew i needed this. thanks for sharing!
setnone
·há 9 dias·discuss
words like 'inequality' and 'defected' tell me theese are ideologically charged expectations which might be the root cause of your disapointment
setnone
·há 10 dias·discuss
non-invasive tech from meta? i don't buy that
setnone
·há 30 dias·discuss
the grooming (marketing) game is strong with anthropic
setnone
·mês passado·discuss
a mistery indeed
setnone
·mês passado·discuss
Is it intelligent then?

Is it accountable? Is it responsible?

Artificially, perhaps
setnone
·mês passado·discuss
cool! i see at least two reasons in the title to upvote this
setnone
·mês passado·discuss
my take it's because of the naming: Amodei, Claude and Mythos have this money-throwing vibe to it
setnone
·mês passado·discuss
if you go this route don't hold your thoughts on the casino itself
setnone
·mês passado·discuss
Claude's 4.6 - 4.7 transition made me discover codex, and with gpt 5.5 there is no way i'm going back
setnone
·há 3 meses·discuss
bunch of Tells HN incoming...
setnone
·há 3 meses·discuss
> they will usually provide extremely useful information

bold claim, they'll provide bunch of words for sure like in this particular tool's response
setnone
·há 3 meses·discuss
absolutely agree: non-1M Opus 4.6 on x20 max was peak AGI

now it's back to regular slop and just to check otherwise i have to spend at least $100
setnone
·há 3 meses·discuss
Good on them for resolving all three issues, but is it any good again?
setnone
·há 3 meses·discuss
some strong advice here for example

https://news.ycombinator.com/item?id=47667504
setnone
·há 3 meses·discuss
Yeah i feel like it's getting cloudy
setnone
·há 3 meses·discuss
It's really hard out there, but trap? who's trapping you?