setnone

260 karmajoined 7 years ago

Submissions

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

7 pointsby setnone11 days ago9 comments

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

1 pointsby setnone3 months ago0 comments

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

3 pointsby setnone8 months ago0 comments

comments

14 minutes agodiscuss

the only ai device that makes any sense is a robot

yesterdaydiscuss

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

2 days agodiscuss

> 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

8 days agodiscuss

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

9 days agodiscuss

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

10 days agodiscuss

non-invasive tech from meta? i don't buy that

30 days agodiscuss

the grooming (marketing) game is strong with anthropic

last monthdiscuss

a mistery indeed

last monthdiscuss

Is it intelligent then?

Is it accountable? Is it responsible?

Artificially, perhaps

last monthdiscuss

cool! i see at least two reasons in the title to upvote this

last monthdiscuss

my take it's because of the naming: Amodei, Claude and Mythos have this money-throwing vibe to it

last monthdiscuss

if you go this route don't hold your thoughts on the casino itself

last monthdiscuss

Claude's 4.6 - 4.7 transition made me discover codex, and with gpt 5.5 there is no way i'm going back

3 months agodiscuss

bunch of Tells HN incoming...

3 months agodiscuss

> they will usually provide extremely useful information

bold claim, they'll provide bunch of words for sure like in this particular tool's response

3 months agodiscuss

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

3 months agodiscuss

Good on them for resolving all three issues, but is it any good again?

3 months agodiscuss

some strong advice here for example

https://news.ycombinator.com/item?id=47667504

3 months agodiscuss

Yeah i feel like it's getting cloudy

3 months agodiscuss

It's really hard out there, but trap? who's trapping you?