Sagittarius

AI

multimodal demo

SHOW HN2023

Legend

Sagittarius

I Remade the Fake Google Gemini Demo, Except Using GPT-4 and It's Real

sagittarius.greg.technology

#gpt-4 vision#multimodal ai#speech recognition#gemini demo

434points
113comments
#69of 3,109 in 2023
Top 3%of 2023 by points

How HN took it

MixedNo clear lean

10 positive, 10 neutral or asking, 1 mixed, 3 critical, out of 24 comments about the project. Thread score +0.33.

Execution: 3 for, 1 againstIdea: 3 for, 1 againstPerformance: 1 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Impressive demo showing a Gemini-style interaction is achievable.

    From 3 comments
    • Wow, this is super cool! From the code it seems like the speech to text and text to speech are using the browser’s built-in features. I always forget those capabilities even exist!
      zainhoda on HN
    • Very cool!
      op00to on HN
    • Thank you for creating this demo. This was the point I was trying to make when the Gemini launch happened. All that hoopla for no reason. Yes - GPT-4V is a beast. I’d even…
      sheepscreek on HN

Objections

  • Demo latency and turn-taking are limited by waiting for finished speech and screenshots.

    From 1 comment
    • The "magic" of the fake Gemini demo was the way it seemed like the LLM was continually receiving audio + video input and knew when to jump in with a response. It appeared to be…
      phire on HN

Questions

  • What are the running costs?

    From 1 comment
    • haha yes it was entirely possible with gpt4v. literally just screenshot and feed in the images and text in chat format, aka “interleaved”. made something similar at a hackathon…
      swyx on HN

Alternatives named

  • Gemini demo video

    From 1 comment
    • haha yes it was entirely possible with gpt4v. literally just screenshot and feed in the images and text in chat format, aka “interleaved”. made something similar at a hackathon…
      swyx on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/38596953)