0123456789ABCDE

these are the visible effects of a hybrid war, not the pranks of script kids

someone, or something, needs to monitor the fridges remotely, which means networked thing with all the cute little details of the IOT tacked to it

edit: these are unlikely to be directly connected to the internet, but rather part of an internal network that got popped, likely a while a go too

nowhere in gp's comment do they claim it was published

the point of the benchmark is not to make `fib()` fast, but to exercise the code in ways everyone can understand. ex: `functools.cache` decorator would mostly show you how fast python `dict`s are — not very useful

glm-5.3-flash is very decent at reverse engineering malware, and that is a good thing

we could spend time answering that question or, as tptacek proposes, diy the solution because the app making app is right there, and answers to your input not Apple/Google's

isn't this just context shifting?

if one were to remove the expressions of excitement from the previous messages would it the model continue to demonstrate that same excitement scaling?

after looking closer at the typesafe's jev, i want to point out that i misunderstood the significance of this jev model

it is the latency that makes it significant

so you can pick the choice with the highest probability?

the example uses an external api, and i don't think they return probabilities from those anyway.

do you have a benchmark name and results we can compare to other models?

this is such a trivial thing to do in DSPY, no one bothered to give it a name…

here's 7 lines

  import os
  import dspy

  lm = dspy.LM("openrouter/z-ai/glm-5.3-flash", api_key=os.environ["OPENROUTER_API_KEY"])
  jev = dspy.Predict('email:str -> choice:Literal["Legitimate", "Spam", "Phishing"]')
  email = "Payroll asks for your password on a non-company sign-in page."
  pred = jev(email=email, lm=lm)
  print(pred.choice)

there are other options, obviously. you can choose to give it some tools, maybe some reasoning stage before picking a choice, and that's on top of the "reasoning" the llm model already does api side

> IRC is not social media.

what is it then?

specifically: what is the medium in which IRC exists, or operates in? are the people using IRC networking with each other, perhaps socializing?