Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework

So, are they planning to announce an optimized coding agent harness as well ? DSv4 flash is a fantastic model, and my daily driver. With reasonix or pi, I can code all day long and pay a few pennies for it. No token anxiety. Whereas the same model with fireworks/openrouter, with zdr thrown in, token costs ratchet up with no explanation. Likely that the model is subsidized for gathering usage data. I am waiting for the day I can run this locally.



They announced it already, read the tech report.

"For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) as the agent framework, using the max reasoning effort level with temperature = 1.0, top_p = 0.95."


> They announced it already

I meant something I could download and run.


Isn't Reasonix [0] DeepSeek's own harness? Or, are they building a new one?

[0] https://reasonix.io/


DS were hiring harness Eng team on x a while ago.


If you're not paying for the model through Open router, then which provider are you buying it from? I thought that if that provider was listed on open router it would be the same price as going directly to the provider? Are you buying from a provider that isn't listed on open router already?


> Are you buying from a provider that isn't listed on open router already

I am using openrouter with zdr guardrail which routes to any provider that supposedly doesnt train on user data. I also use fireworks (directly, not via openrouter) which is a provider promising zdr and has a bunch of open weights models. My issue is that these zdr providers dont transparently disclose caching/tokens etc and so they end up being far more expensive than directly using DS.


Have you tried Novita? They're zdr and I find they usually have better cache hit rates than fireworks. No affiliation.


Thanks for the input. Let me check it out.


> OpenRouter has taken the stance that in-memory caching of prompts is not considered “retaining” data, and we therefore allow endpoints/models with implicit caching to be hit when a ZDR routing policy is in effect. [0]

OpenRouter doesn’t list DeepSeek as ZDR combined with Caching. Thanks for the tip of Fireworks as Fireworks has Zero Data Retention by default. [1]

[0] https://openrouter.ai/docs/guides/features/zdr

[1] https://docs.fireworks.ai/guides/security_compliance/data_ha...




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: