by sam1234apter on 12/13/23, 3:09 PM with 109 comments
by gregsadetsky on 12/13/23, 5:59 PM
Gemini Pro is... not great. In one test, I asked what gesture I was making (while showing a thumbs up) -- it said thumbs down and "The image is a commentary on the changing nature of truth".
I just just made a heads-to-heads comparison -- you can watch it here: https://www.youtube.com/watch?v=1RrkRA7wuoE
Code is here: https://github.com/gregsadetsky/sagittarius
by chamoda on 12/13/23, 3:20 PM
by isalmon on 12/13/23, 5:40 PM
Doing this with ChatGPT 4.0 for months and months did not cause this type of behavior.
by pesfandiar on 12/13/23, 5:52 PM
[1] https://makersuite.google.com/app/prompts/blog-post-creator
by dudus on 12/13/23, 4:17 PM
by sam1234apter on 12/13/23, 3:09 PM
Developers have a free quota and access to a full range of features including function calling, embeddings, semantic retrieval, custom knowledge grounding, chat functionality and more. It supports 38 languages across 180+ countries.
by georgehill on 12/13/23, 3:33 PM
Wait only in the US?
Edit: I can access it through the Google Cloud Console.
by ianbicking on 12/13/23, 10:02 PM
It looks like a fairly easy swap-in for GPT. "messages" becomes "content". Some of the configuration parameters are slightly different (topP/etc), but I have never put in the effort to understand the practical effect of those so I never tweak their values.
The messages themselves are a list of "parts", which allows mixed media messages. This feels a little cleaner than how GPT has handled messages being extended.
Instead of role: "assistant" they use role: "model". There's no role: "system" – presumably you just shove everything into user messages. You can also leave off the role... and I assume that means default to "user" but it's not clear if it's 100% equivalent...?
There's a bunch of moderation parameters, which seems like a good idea. OpenAI has a moderation endpoint you can use to preflight check your input, but doing it all at once makes more sense. There's four categories and you can adjust your sensitivity to each (and turn off blocking at entirely). The sensitivity is not about how extreme the violation is, but how likely it is a violation. So it's not like a G/PG/PG-13/etc rating. Just a question of how many false positives/negatives you want.
There's functions, though they are in beta (whatever that means): https://ai.google.dev/docs/function_calling – they look very very similar to GPT functions. They don't have the "JSON response" that GPT has, but that seems mostly redundant with functions anyway.
I have no idea how well prompts translate, but it feels like the API is an easy translation. And importantly everything is semantically equivalent, you don't have to make one pretend it is the other, like turning a completion API into a chat API.
Given the generous free tier I feel fairly motivated to swap in Gemini and try to ship experiments that I've sat on until now.
by brrrrrm on 12/13/23, 4:50 PM
Node.js:
const model = genAI.getGenerativeModel({ model: "gemini-pro-vision"});
const result = model.generateContent({ contents: [{parts: [
{text: "What’s in this photo?"},
{inlineData: {data: imgBase64, mimeType: 'image/png'}}
] }] })
const model = genAI.getGenerativeModel({ model: "gemini-pro-vision"});
const result = await model.generateContent([
"What’s in this photo?",
{inlineData: {data: imgDataInBase64, mimeType: 'image/png'}}
]);by lovasoa on 12/13/23, 5:48 PM
I will happily let google buy me for that price.
by thedangler on 12/13/23, 3:50 PM
by legendofbrando on 12/13/23, 4:38 PM
by AlmostSchurLie on 12/13/23, 5:01 PM
by vibhajaiman on 12/15/23, 8:58 AM
by vibhajaiman on 12/15/23, 8:58 AM
by andre-z on 12/13/23, 3:56 PM
by SubiculumCode on 12/13/23, 4:51 PM
by roschdal on 12/13/23, 7:50 PM
by prakhar897 on 12/13/23, 6:13 PM
by ziga9 on 12/13/23, 7:39 PM
by zlg_codes on 12/13/23, 9:58 PM
I'm sure it's just an accident.
by tanyongsheng on 12/13/23, 4:51 PM
by replwoacause on 12/13/23, 4:40 PM
by fotcorn on 12/13/23, 3:49 PM
Some basic prompts, which are answered correctly most of the time by ChatGPT4:
There are 31 books in my house. I read 2 books over the weekend. How many books are still in my house?
> 29 books
Julia has three brothers, each of them has two sisters. How many sisters does Julia have?
> Three
If you place an orange below a plate in the living room, and then move the plate to the kitchen, where is the orange now?
> Under the plate in the kitchen.
So, not great.
by imdsm on 12/13/23, 3:55 PM
Get API key, takes me to makersuite, where I get a create API key button that errors. Then when I reload the page, I get a straight forbidden page.
HP said it best, you have to isolate the team from the bigger company to allow them to work as an effective startup. How can solo-preneurs provide better UX & onboarding while doing 16 other jobs than Google can with multi-billion dollar budgets?
by verdverm on 12/13/23, 5:00 PM
- https://cloud.google.com/vertex-ai (marketing page)
- https://cloud.google.com/vertex-ai/docs (docs entry point)
- https://console.cloud.google.com/vertex-ai (cloud console)
- https://console.cloud.google.com/vertex-ai/model-garden (all the models)
- https://console.cloud.google.com/vertex-ai/generative (studio / playground)
VertexAI is the umbrella for all of the Google models available through their cloud platform.
You want the last link if you are looking for a ChatGPT like experience, with the ability to also adjust the parameters, so more like a UI on top of the API
by alexb_ on 12/13/23, 3:38 PM
by behnamoh on 12/13/23, 3:36 PM
by martythemaniak on 12/13/23, 4:29 PM
- 60 queries per minute free - about 1/5th the price of GPT3.5 Turbo - priced per char, not per token - same image pricing as GPT4 150x150
by yeldarb on 12/13/23, 5:34 PM