HackerTrans
TopNewTrendsCommentsPastAskShowJobs

setnone

261 karmajoined 7 anni fa

Submissions

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

7 points·by setnone·11 giorni fa·9 comments

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

1 points·by setnone·3 mesi fa·0 comments

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

3 points·by setnone·8 mesi fa·0 comments

comments

setnone
·10 ore fa·discuss
the only ai device that makes any sense is a robot
setnone
·l’altro ieri·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
·l’altro ieri·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
·9 giorni fa·discuss
very well done, never knew i needed this. thanks for sharing!
setnone
·9 giorni fa·discuss
words like 'inequality' and 'defected' tell me theese are ideologically charged expectations which might be the root cause of your disapointment
setnone
·11 giorni fa·discuss
non-invasive tech from meta? i don't buy that
setnone
·mese scorso·discuss
the grooming (marketing) game is strong with anthropic
setnone
·mese scorso·discuss
a mistery indeed
setnone
·mese scorso·discuss
Is it intelligent then?

Is it accountable? Is it responsible?

Artificially, perhaps
setnone
·mese scorso·discuss
cool! i see at least two reasons in the title to upvote this
setnone
·mese scorso·discuss
my take it's because of the naming: Amodei, Claude and Mythos have this money-throwing vibe to it
setnone
·mese scorso·discuss
if you go this route don't hold your thoughts on the casino itself
setnone
·mese scorso·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
·3 mesi fa·discuss
bunch of Tells HN incoming...
setnone
·3 mesi fa·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
·3 mesi fa·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
·3 mesi fa·discuss
Good on them for resolving all three issues, but is it any good again?
setnone
·3 mesi fa·discuss
some strong advice here for example

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