HackerLangs
トップ新着トレンドコメント過去質問紹介求人

ctxc

806 カルマ登録 5 年前
Curious, love all things tech! Have a cool article, need a second opinion or want to hang out? Hit me up. Send me a message on [email protected] or find socials in https://dvsj.in#contact

投稿

Human Intelligence Portal (demo, awareness)

dvsj.in
1 ポイント·投稿者 ctxc·4 か月前·0 コメント

Agentic browsers: a note for my friends

dvsj.in
2 ポイント·投稿者 ctxc·7 か月前·0 コメント

[untitled]

1 ポイント·投稿者 ctxc·8 か月前·0 コメント

Ask HN: Have you directly authored a high-profile massive bug? How does it feel?

3 ポイント·投稿者 ctxc·8 か月前·3 コメント

Buzzwords for the Busy: LLMs

dvsj.in
1 ポイント·投稿者 ctxc·8 か月前·1 コメント

The kind of company I want to be a part of

dvsj.in
162 ポイント·投稿者 ctxc·8 か月前·168 コメント

Making the Most of a HN Launch

dvsj.in
1 ポイント·投稿者 ctxc·9 か月前·0 コメント

The Perfect Hacker News Launch (MagicPatterns HN Login Button)

dvsj.in
2 ポイント·投稿者 ctxc·9 か月前·0 コメント

Security 101 for devs: a presentation (2014)

dvsj.in
3 ポイント·投稿者 ctxc·10 か月前·0 コメント

コメント

ctxc
·一昨日·議論
It was always this way!
ctxc
·一昨日·議論
Yeah weird, bc I just checked and it isn't oss. Only the SDKs are OSS, which...doesn't help much
ctxc
·11 日前·議論
/s not needed, it's the easiest path
ctxc
·先月·議論
(you mean it's _not_ AI generated)
ctxc
·先月·議論
I feel like with time, 50 is the new 70.
ctxc
·2 か月前·議論
Those numbers make sense to me...120 million input tokens is like 120 sessions of hitting the full context limit, which seems like a lot to me though
ctxc
·2 か月前·議論
Haha! Made me chuckle
ctxc
·2 か月前·議論
Reads like a LOT of tokens to me. What does your usage /workflow look like? I'm v curious because although I do use Claude code, my token counts aren't nearly as much

I want to know if I'm missing something cool!
ctxc
·2 か月前·議論
When you have a general idea of what smells bad vs what's okay...why?

I'd rather get it from the LLM and review
ctxc
·2 か月前·議論
[dead]
ctxc
·2 か月前·議論
They report an hour less than average sleep time the first 3 months?!

How did get so lucky?
ctxc
·2 か月前·議論
WOW YES OMG

do you remember what the wrestling kinda game with ed ed and eddy was?
ctxc
·3 か月前·議論
Out of curiosity, what kind of custom harness are you thinking?
ctxc
·3 か月前·議論
I do something tangential. If you can pick out identifiers for these pages with deterministic features (financial pages have the most numbers on the page, or have the word "director", "general manager" and "managing director" on the same page, etc)

Pick those pages out and pipe only those to the llm

Luckily I work with excel w lots of sheets and don't need to do pdf to text conversion etc
ctxc
·3 か月前·議論
Scale, my friend, scale...
ctxc
·3 か月前·議論
Interesting, I'd love to know more. Are parts of it public?
ctxc
·3 か月前·議論
haha, sweet. One of the cooler things I've read lately
ctxc
·3 か月前·議論
I was going to type you a sympathetic message and took a peek at your profile, and...well that's quite a resume you got there!
ctxc
·3 か月前·議論
Accountability. Same reason I want to read human written content rather than obvious AI: both can be equally shit, but at least with humans there's a high probability of the aspirational quality of wanting to be considered "good"

With AI I have no way of telling if it was from a one line prompt or hundreds. I have to assume it was one line by default if there's no human sticking their neck out for it.
ctxc
·4 か月前·議論
I took ~ to be a "singing tone" for some reason till I saw sibling and realized it might be an attempted strikethrough xD