The past DeepSeek models and now these new checkpoints score very badly on the ArtificialAnalysis AA-Omniscience and hallucination rate benchmarks. I wonder where that's from? Maybe they're overindexing on coding even more than others? I can't say I've noticed it in my (coding) usage so far, has anyone seen it make up potential root causes or other speculative stuff more than other models?
DeepSeek V4 Pro 0813
361–370 of 493 posts
Re: DeepSeek V4 Pro 0813
#362Earlier quoted context omitted.
I don’t understand why people are calling these transformers models non-deterministic? Are you referring to the temperature parameter? I haven’t played with transformer internals in a while but my understanding is that if the temperature is fixed at a value where the top logit is always picked, then because they weights are fixed, the exact same input should produce the exact same output. Am I missing something?
I think people are wrapping that across the English language. In English, these two tasks are exactly the same: "Would you hand me that item?" "Please hand me that item" But when posed to the LLM, they generate different outputs. One character difference in the prompt might be a whole different output. People who aren't programmers mostly don't know that there's any difference. They asked for the same thing, it knows…
Yeah, that's bullshit.
Depending on my mental state, status with the person and many other factors each of them may trigger both many different internal thoughts, looks, body expressions and even outcomes.
Re: DeepSeek V4 Pro 0813
#363So flash is 52 points on artificial analysis, and pro is 53
Re: DeepSeek V4 Pro 0813
#364Earlier quoted context omitted.
Open doesn't always refer to the code. Just like their previous project, it refers to an open marketplace where anybody can sign up to sell access to models. But it'd still be nice to post to wait an extra minute to find some other page/new url from deepseek for it instead of posting that it exists somewhere.
it's not open, I know people rejected by them (then they went to my site to be listed Trustedrouter.com)
You accept any and every registration? I think that goes a bit beyond an open market and into a completely unregulated one I'd never want to route my sessions through. Thanks for providing the conflicting interest disclosure though, too often people don't bother.
Re: DeepSeek V4 Pro 0813
#365Nice bicycle chain, the little basket with a fish didn't show up in the right place: https://tools.simonwillison.net/markdown-svg-renderer#url=ht...
I assume this isn't watermarked...
Re: DeepSeek V4 Pro 0813
#366The past DeepSeek models and now these new checkpoints score very badly on the ArtificialAnalysis AA-Omniscience and hallucination rate benchmarks. I wonder where that's from? Maybe they're overindexing on coding even more than others? I can't say I've noticed it in my (coding) usage so far, has anyone seen it make up potential root causes or other speculative stuff more than other models?
Yeah. I stopped ising deepseek v4 flashbecause it is awful (even worse than my local qwen3.6 35B model) at multilingual prose.
Re: DeepSeek V4 Pro 0813
#367The past DeepSeek models and now these new checkpoints score very badly on the ArtificialAnalysis AA-Omniscience and hallucination rate benchmarks. I wonder where that's from? Maybe they're overindexing on coding even more than others? I can't say I've noticed it in my (coding) usage so far, has anyone seen it make up potential root causes or other speculative stuff more than other models?
0731 is definitely tuned for coding. I mean: https://gertlabs.com/rankings?mode=agentic_coding
But it is also a decent translator from English to Czech in my experience.
Re: DeepSeek V4 Pro 0813
#368Earlier quoted context omitted.
Is this a new rule? I've seen some popular blog posts reposted here several times and still highly upvoted.
I _think_ that has always been based on discretion of the mods. It’s only allowed after some period of time and if popular enough.
The software detects when an identical URL is submitted and will mark it as a duplicate (with certain conditions like how recently it was last submitted and whether it had any front page time and discussion).
When similar URLs or different versions of the same story are submitted and get votes/comments, we have to use discretion to work out which URL is best, who submitted first, which discussion is most active/healthy, and we'll try to consolidate the discussion into one thread with the most informative/canonical URL as the main link.
Re: DeepSeek V4 Pro 0813
#369Re: DeepSeek V4 Pro 0813
#370DS Pro is what I hoped it would be. I have used it as an auditor for a couple of implementations, and the work is solid. This will allow me to split the work between 5.6 Sol and DS Pro.