HackerLangs
TopNewTrendsCommentsPastAskShowJobs

setnone

260 karmajoined 7 年前

Submissions

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

7 points·by setnone·11 天前·9 comments

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

1 points·by setnone·3 個月前·0 comments

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

3 points·by setnone·8 個月前·0 comments

comments

setnone
·昨天·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
·前天·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
·8 天前·discuss
very well done, never knew i needed this. thanks for sharing!
setnone
·9 天前·discuss
words like 'inequality' and 'defected' tell me theese are ideologically charged expectations which might be the root cause of your disapointment
setnone
·10 天前·discuss
non-invasive tech from meta? i don't buy that
setnone
·30 天前·discuss
the grooming (marketing) game is strong with anthropic
setnone
·上個月·discuss
a mistery indeed
setnone
·上個月·discuss
Is it intelligent then?

Is it accountable? Is it responsible?

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

https://news.ycombinator.com/item?id=47667504
setnone
·3 個月前·discuss
Yeah i feel like it's getting cloudy
setnone
·3 個月前·discuss
It's really hard out there, but trap? who's trapping you?
setnone
·3 個月前·discuss
definitely a great use of LLMs