Hacker News: setnone

New comment by setnone in "Position: LLMs Can't Jump"

setnone — Wed, 05 Aug 2026 13:34:52 +0000

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

New comment by setnone in "Ask HN: What if there was an 8th day of the week?"

setnone — Wed, 05 Aug 2026 10:39:15 +0000

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

New comment by setnone in "Ask HN: What if there was an 8th day of the week?"

setnone — Wed, 05 Aug 2026 08:40:22 +0000

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

New comment by setnone in "Ask HN: Dear Anthropic, can we please have thought traces back?"

setnone — Wed, 05 Aug 2026 08:24:54 +0000

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

New comment by setnone in "Codex Resets"

setnone — Sun, 19 Jul 2026 08:09:38 +0000

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

New comment by setnone in "Ask HN: Do you say please and thank you to your LLMs?"

setnone — Fri, 17 Jul 2026 10:57:05 +0000

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

New comment by setnone in "Ask HN: I feel like I've lost my identity due to AI"

setnone — Fri, 17 Jul 2026 08:21:26 +0000

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

New comment by setnone in "Apple sues OpenAI, accuses ex-employees of stealing trade secrets"

setnone — Sat, 11 Jul 2026 05:17:12 +0000

the only ai device that makes any sense is a robot

New comment by setnone in "GPT-5.6"

setnone — Thu, 09 Jul 2026 18:47:59 +0000

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

New comment by setnone in "A new way to reflect on how you use Claude"

setnone — Thu, 09 Jul 2026 16:02:08 +0000

> 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

New comment by setnone in "Show HN: A graph paper generator that renders vector PDFs in the browser"

setnone — Thu, 02 Jul 2026 17:38:52 +0000

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

New comment by setnone in "Tell HN: I'm not excited for Fable and am disappointed in Karpathy"

setnone — Thu, 02 Jul 2026 09:08:39 +0000

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

New comment by setnone in "From brain waves to words: a new path to communication without surgery"

setnone — Tue, 30 Jun 2026 22:23:26 +0000

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

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

setnone — Tue, 30 Jun 2026 15:27:25 +0000

Hi HN, just want to rant and see if anybody can relate.

The product is not the same as i signed up for few month ago and the same shift i've experienced with Claude Code on Opus 4.6-4.7

The best way to describe the difference is you hire a reliable 'intelligent' tech lead who 'gives a shit' and in some time you eventually get over-confident junior dev that acts as destructive token burner.

No thinking during the process, not even really following instructions.

It's pretty much a binary shift that happens and in my experience can't be cured with prompting.

There is no way to actually tell what's happening under the hood with models but the difference is noticeable from the first reply.

I'm on max, GPT 5.5 extra high, always mindful of context window, use plan mode etc.

Is it the model: dumbing down or quietly route to another model for some reason? Is it the harness? or is it my imagination?

Curious what's your recent experience.

PS: frontier models should add "give-a-shit: max" along with 'thinking: max', 'effort: max' and make them actually work.

Comments URL: https://news.ycombinator.com/item?id=48734115

Points: 7

# Comments: 9

New comment by setnone in "Anthropic requires 30 day data retention for Fable and Mythos"

setnone — Thu, 11 Jun 2026 09:18:59 +0000

the grooming (marketing) game is strong with anthropic

New comment by setnone in "Google employees internally share memes about how its AI sucks"

setnone — Thu, 04 Jun 2026 16:20:23 +0000

a mistery indeed

New comment by setnone in "Artificial intelligence is not conscious – Ted Chiang"

setnone — Thu, 04 Jun 2026 12:39:47 +0000

Is it intelligent then?

Is it accountable? Is it responsible?

Artificially, perhaps

New comment by setnone in "Show HN: Nutrepedia – nutrition info in 29 locales built with Clojure and Htmx"

setnone — Wed, 03 Jun 2026 17:49:35 +0000

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

New comment by setnone in "Anthropic surpasses OpenAI to become most valuable AI startup"

setnone — Sat, 30 May 2026 15:09:30 +0000

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

New comment by setnone in "Claude Opus 4.8"

setnone — Thu, 28 May 2026 19:34:14 +0000

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