PhilippGille
Joined 9 years ago
Karma
1,307
Submissions
424
Member since
Aug 4
Recent submissions
Comment · 13 days ago
Kagi has an official MCP server [1], where you set the API key. MCP use is always by an LLM, so this seems to be at odds with their TOS.
Comment · 1 month ago
It would be nice to disclose that you're the creator of the tool which you are promoting here.
Comment · 1 month ago
Websites can just present information.
When I visit a website, I'm usually looking for information and not for a message.
Comment · 1 month ago
Comment · 1 month ago
> Open source does not apply to AI
Isn't that a bit overgeneralized?
There's more than weights for the Olmo models for example: https://allenai.org/olmo
Similar for Nvidia's Nemotron models IIRC.
Artificial Analysis has an "openness" ranking: [1]
[1] https://artificialanalysis.ai/models?model-filters=open-sour...
Comment · 2 months ago
Token usage is generally lower in greenfield projects.
Comment · 2 months ago
NovitaAI is already hosting it: https://openrouter.ai/z-ai/glm-5.3-flash#providers
Comment · 2 months ago
Official blog post: https://blogs.nvidia.com/blog/geforce-now-thursday-linux-nat...
Comment · 2 months ago
According to OpenRouter, DeepSeek trains on input. At least when disabling all providers that train on your data, DeepSeek gets disabled.
Other providers don't.
You can also choose to route to ZDR only.
https://openrouter.ai/deepseek/deepseek-v4-flash-0731#provid...
Comment · 2 months ago
Existing recent discussion with 127 points, 68 comments: https://news.ycombinator.com/item?id=49246704
Comment · 2 months ago
98.33 according to https://mrshu.github.io/github-statuses/
Comment · 3 months ago
Yes that's my point. The old and the new version are different in capabilities, but now when someone talks about DeepSeek V4 Flash (in benchmarks, on inference providers), you don't know which exact version it's about.
Some providers like OpenRouter now call it `deepseek-v4-flash-0731`, but even in places like here on HackerNews people say things like "Sonnet is better than DeepSeek" without specifying a version or a reasoning effort, certainly no one will mention that `-0731` suffix when talking about DeepSeek V4 Flash.
Comment · 3 months ago
That's what I mean. On DeepSeek it's now just `deepseek-v4-flash`, while OpenRouter calls it `deepseek/deepseek-v4-flash-0731`, so now when someone talks about DeepSeek V4 Flash, like in benchmarks, or other inference providers, which version do they actually mean?
The `-0731` style suffix is worse compared to a proper version bump like V4.1.
meet.hn/city/de-Leipzig