Just tested it via openrounter in the Pi Coding agent and it regularly fails to use the read and write tool correctly, very disappointing. Anyone know a fix besides prompting "always use the provided tools instead of writing your own call"
DeepSeek v4
191–200 of 1001 posts
Re: DeepSeek v4
#192giving meta a run for its money, esp when it was supposed to be the poster child for OSS models. deepseek is really overshadowing them rn
Re: DeepSeek v4
#193https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.
I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits. As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same resu…
eh idk. until yesterday opus was the one that got spatial reasoning right (had to do some head pose stuff, neither glm 5.1 nor codex 5.3 could "get" it) and codex 5.3 was my champion at making UX work.
So while I agree mixed model is the way to go, opus is still my workhorse.
Re: DeepSeek v4
#194There's something heartwarming about the developer docs being released before the flashy press release.
Where's the training data and training scripts since you are calling this open source ? Edit: it seems "open source" was edited out of the parent comment.
Weights are the source, training data is the compiler.
Re: DeepSeek v4
#195https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main... Model was released and it's amazing. Frontier level (better than Opus 4.6) at a fraction of the cost.
I don't think we need to compare models to Opus anymore. Opus users don't care about other models, as they're convinced Opus will be better forever. And non-Opus users don't want the expense, lock-in or limits. As a non-Opus user, I'll continue to use the cheapest fastest models that get my job done, which (for me anyway) is still MiniMax M2.5. I occasionally try a newer, more expensive model, and I get the same resu…
Is Opus nerfed somehow in Copilot? Ive tried it numerous times, it has never reallt woved me. They seem to have awfully small context windows, but still. Its mostly their reasoning which has been off
Codex is just so much better, or the genera GPT models.
Re: DeepSeek v4
#196Earlier quoted context omitted.
Their Chinese announcement says that, based on internal employee testing, it is not as good as Opus 4.6 Thinking, but is slightly better than Opus 4.6 without Thinking enabled.
That's super interesting, isn't Deepseek in China banned from using Anthropic models? Yet here they're comparing it in terms of internal employee testing.
They use VPN to access. Even Google Deepmind uses Anthropic. There was a fight within Google as to why only DeepMind is allowed to Claude while rest of the Google can't.
Re: DeepSeek v4
#197Re: DeepSeek v4
#198> pricing "Pro" $3.48 / 1M output tokens vs $4.40 I’d like somebody to explain to me how the endless comments of "bleeding edge labs are subsidizing the inference at an insane rate" make sense in light of a humongous model like v4 pro being $4 per 1M. I’d bet even the subscriptions are profitable, much less the API prices. edit: $1.74/M input $3.48/M output on OpenRouter
My thoughts exactly. I also believe that subscription services are profitable, and the talk about subsidies is just a way to extract higher profit margins from the API prices businesses pay.
Re: DeepSeek v4
#199Just tested it via openrounter in the Pi Coding agent and it regularly fails to use the read and write tool correctly, very disappointing. Anyone know a fix besides prompting "always use the provided tools instead of writing your own call"
They have just released it, give it some time, they probably haven't pretested it with Pi
Re: DeepSeek v4
#200Earlier quoted context omitted.
This should not be the top comment on every model release post. It's getting tiring.
This should be the bottom comment on the pelican comment on every model release post.
Clearly the top comment should be "Imagine a beowulf cluster of Deepseek v4!"