←back to thread

Mercury: Ultra-fast language models based on diffusion

(arxiv.org)
566 points PaulHoule | 2 comments | 07 Jul 25 12:31 UTC | HN request time: 0s | source
Show context
armcat ◴[07 Jul 25 20:45 UTC] No.44494518[source]▶
I've been looking at the code on their chat playground, https://chat.inceptionlabs.ai/, and they have a helper function `const convertOpenAIMessages = (convo) => { ... }`, which also contains `models: ['gpt-3.5-turbo']`. I also see in API response: `"openai": true`. Is it actually using OpenAI, or is it actually calling its dLLM? Does anyone know?

Also: you can turn on "Diffusion Effect" in the top-right corner, but this just seems to be an "animation gimmick" right?

replies(1): >>44494556 #
Alifatisk ◴[07 Jul 25 20:51 UTC] No.44494556[source]▶
The speed of the response is waaay to quick for using OpenAi as backend, it's almost instant!
replies(1): >>44494689 #
armcat ◴[07 Jul 25 21:08 UTC] No.44494689[source]▶
I've been asking bespoke questions and the timing is >2 seconds, and slower than what I get for the same questions to ChatGPT (using gpt-4.1-mini). I am looking at their call stack and what I see: "verifyOpenAIConnection()", "generateOpenAIChatCompletion()", "getOpenAIModels()", etc. Maybe it's just so it's compatible with OpenAI API?
replies(1): >>44495069 #
1. martinald ◴[07 Jul 25 21:56 UTC] No.44495069[source]▶
Check the bottom, I think it's just some off the shelf chat UI that uses OpenAI compatible API behind the scenes.
replies(1): >>44495377 #
2. armcat ◴[07 Jul 25 22:49 UTC] No.44495377[source]▶
Ah got it, it looks like it's a whole bunch of things so it can also interface with ollama, and other APIs.