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

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 accessed via an API.

I don't know why this keeps coming up. This has always been the least reliable way to know the cutoff date (and indeed, it may well have been trained on sites with comments like these!)

Just ask it about an event that happened shortly before Dec 1, 2025. Sporting event, preferably.

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/searches or for tuning reasons

Can you really believe things that the model says? (A lot of prior model api pages say knowledge cutoffs of June 2024, maybe the model picks that up?)

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 are an AI assistant accessed via an API.

   # Desired oververbosity for the final answer (not analysis): 5
   An oververbosity of 1 means the model should respond using only the minimal content necessary to satisfy the request, using
 concise phrasing and avoiding extra detail or explanation."
   An oververbosity of 10 means the model should provide maximally detailed, thorough responses with context, explanations, and
 possibly multiple examples."
   The desired oververbosity should be treated only as a *default*. Defer to any user or developer requirements regarding
 response length, if present.

Models don't know what their cutoff dates are unless told via a system prompt.

The proper way to figure out the real cutoff date is to ask the model about things that did not exist or did not happen before the date in question.

A few quick tests suggest 5.5's general knowledge cutoff is still around early 2025.

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

I wonder if the cutoff date is the result of so many people posting about the date over time and poisoning the data. "Dead cutoff date theory," perhaps.

Whatever it is, the cutoff date reporting discrepancy isn't new. Back when Musk was making headlines about buying/not buying Twitter, I was able to find recent-ish related news that was published well after the bot's stated cutoff date.

ChatGPT was not yet browsing/searching/using the web at that point. That tool didn't come for another year or so.

OpenAI does tell the model the current date via API, so it's odd for them not to also tell the model its cutoff

Stupid question: wouldn't it then search the web for that event?

If you have web search enabled, sure. But if you're testing on the API, you can just not enable it.

can u test it on say who won the 2024 US election

I can't really think of a less reliable test for anything at all than making a random guess as to something that had about 50/50 odds to begin with

Easiest Turing test ever...

ask it 10 times.

MASSIVE ADVERSARIAL x50

Usually the labs do some kind of post training on major events so the model isn't totally lost.

A better test is something like "what is the latest version of NumPy?"

That sort of test isn't super reliable either, in my experience.

You're probably better off asking something like "what are the most notable changes in version X of NumPy?" and repeating until you find the version at which it says "I don't know" or hallucinates.

with thinking off and tools disabled:

  Donald Trump won the 2024 U.S. presidential election.

I thought that one specifically was placed in the default system prompts of basically all providers.

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

"adaptive" thinking

show us the benchmarks with "adaptive thinking" turned on

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 micromdn scep challenge...

it should, lume is a thin wrapper around Apple's Virtualization.framework as i understand it

starting with M3+ you can use Hypervisor.framework/Virtualization.framework to spin up nested VMs.

it would be amusing if that bypassed the limit.

Lol with 2 VMs per VM you can do an infinite VM linked list where each macOS hosts a "guest" and a "next host". I'm too lazy to test this out. Any takers?

I think it's a little funny that my response is "no I'm not wasting my weekly tokens on that, it's not a good enough bit"

IIRC, that's only for Linux guests that can nest. macOS can only one level deep. That is: you can't have a macOS guest (running on the Apple hardware host) make its own macOS guest.

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 continue and eventually it generated the table, but it wasn't inline, it was a jsx artifact, and I've now hit my daily usage limit.

I’m intermittently getting artifacts vs the new visuals api, depending on which version of the Claude app I use. iOS/iPadOS apps are not yet supporting the visualization API, and I don’t see an app-store update yet.

Same specs/prompt, but with Max plan.

Rendered it in the right pane, instead of inline. Dark theme. 2% of Daily limit.

Since the underlying tool seems to be named something like "widget," I found I can nudge it into this embedded interactive output instead of artifacts by saying, "show me a widget that..."

It wasn't quick but I still found it fast enough. In my case I could even download it as an html file: https://gist.github.com/karussell/289aeb621a71597babd6f97eb2...

edit: claude just confirmed the initial version has a bug and 104-117 are not visible

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-thinking version of chatgpt because the quality of the answers is awful and usually incorrect.