Viewing profile — czk
czk
HN member- Joined
- Thu, Feb 28, 2013, 1:07 AM UTC
- HN karma
- 467
- Public activity
- 128 items
- HN profile
- View on Hacker News ↗
About czk
No profile information was provided.
Recent public activity
-
comment
Comment #49212240
make your only legit users mine fake crypto to access your site, only costs them 5% battery on an android device
- comment
-
comment
Comment #48700496
steady lads, deploying more capital
-
comment
Comment #48609673
if you're benchmaxxing then maybe bigger doesnt always mean better, but for general intelligence and big model smell, that couldn't be further from the truth the oss models are imp…
- comment
-
comment
Comment #47954662
There was also a bug where you could cancel the subscription via the iOS app store and if you never opened the iOS claude app again, you'd keep the subscription forever and could u…
-
comment
Comment #47895010
They mention it uses MXFP4 quant which is a blackwell capability but it looks like this is also supported by ascend 950 series according to marketing material
-
comment
Comment #47894953
i wonder if they put an older cutoff date into the prompt intentionally so that when asked on more current events it leans towards tool calls / web searches for tuning
-
comment
Comment #47894919
the model obviously knows things after the reported date but its just curious that it reports that date consistently could be they do it intentionally to encourage more tool calls/…
-
comment
Comment #47894863
with thinking off and tools disabled: Donald Trump won the 2024 U.S. presidential election.
-
comment
Comment #47894858
you cant but its pretty reproducible across api and codex and other agents so i just thought it was odd. full text it gives: Knowledge cutoff: 2024-06 Current date: 2026-04-24 You …
-
comment
Comment #47894613
API page lists the knowledge cutoff as Dec 01, 2025 but when prompting the model it says June 2024. Knowledge cutoff: 2024-06 Current date: 2026-04-24 You are an AI assistant acces…
- comment
-
comment
Comment #47868177
Memory bandwidth is the biggest L on the dgx spark, it’s half my MacBook from 2023 and that’s the biggest tok/sec bottleneck
-
comment
Comment #47799995
"adaptive" thinking
-
comment
Comment #47799124
show us the benchmarks with "adaptive thinking" turned on
-
comment
Comment #47796468
the MDM profile requirement is suspect though I get why they are doing it. but it doesn't inspire confidence to see that their profile is unsigned and still using the default micro…
-
comment
Comment #47734271
it should, lume is a thin wrapper around Apple's Virtualization.framework as i understand it
-
comment
Comment #47734246
starting with M3+ you can use Hypervisor.framework/Virtualization.framework to spin up nested VMs. it would be amusing if that bypassed the limit.
-
comment
Comment #47354145
I tried the periodic table in their examples using sonnet 4.6 on the $20/mo plan. After a few minutes Claude told me it reached the max message length and bailed. I pressed continu…
-
comment
Comment #47240844
claude models with 'extended thinking' toggled answer very quickly and the quality of the answer is far ahead of what gpt 5.2 'instant' provides. i wont even bother using the non-t…
-
comment
Comment #46891741
i spend most of my time with claude thinking about when my daily usage limit is going to reset
-
comment
Comment #46727967
“After creating a new account, I can confirm the quota drains 2.5x–3x slower. So basically Max (5x) on an older accounts is almost like Pro on a new one in terms of quota. Pretty b…
-
comment
Comment #46714250
claude has half the context window size of codex and blows through a good percentage of it right off the bat by injecting a system prompt the size of don quixote
-
comment
Comment #46712298
it sounds like the data can be involuntarily disclosed to an external third party (the attacker’s domain) purely because someone reviewed logs that auto-load remote images their lo…