Maybe OpenAI wont nerf chatgpt!
Gemini AI
981–990 of 1001 posts
Re: Gemini AI
#982Very impressive! I noticed two really notable things right off the bat: 1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub i…
The biggest advantage of Bard is the speed, it's practically instant. I asked: How would I go about creating a sandbox directory for a subordinate user (namespaced user with subuid - e.g. uid 100000), that can be deleted as the superior user (e.g. uid 1000)? I want this to be done without root permissions. Both said that it's impossible, which is the the generally accepted answer. I then added: I don't care about dat…
> (namespaced user with subuid - e.g. uid 100000), that can be deleted as the superior user (e.g. uid 1000)
I'm afraid I don't know what this means. That when you delete uid 1000, uid 100000 also gets deleted? Or, only user 1000 has permission to delete user 100000 ?
Re: Gemini AI
#983Good effort but still far behind. The biggest problem is it's unable to provide factual information with any accuracy. Chatgpt has maybe 50-80% accuracy depending on context. Bard has 10-20%.
Re: Gemini AI
#984Very impressive! I noticed two really notable things right off the bat: 1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub i…
Those impressive demos, e.g. the cup shuffling seem to have been "staged". The end results are correct, but the method of getting them is nowhere near as fluid and elegant as in the demo. They used a series of still images with carefully crafted prompts. More info: https://developers.googleblog.com/2023/12/how-its-made-gemin...
Re: Gemini AI
#985This demo is nuts: https://youtu.be/UIZAiXYceBI?si=8ELqSinKHdlGlNpX
How real is it though? This blog post says In this post, we’ll explore some of the prompting approaches we used in our Hands on with Gemini demo video. which makes it sound like they used text + image prompts and then acted them out in the video, as opposed to Gemini interpreting the video directly. https://developers.googleblog.com/2023/12/how-its-made-gemin...
It's always like this isn't it. I was watching the demo and thought why ask it what duck is in multiple languages? Siri can do that right now and it's not an ai model. I really do think we're getting their with the ai revolution but these demos are so far from exciting, they're just mundane dummy tasks that don't have the nuance of everything we really interact and would need help from an ai with
Re: Gemini AI
#986Very impressive! I noticed two really notable things right off the bat: 1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub i…
Those impressive demos, e.g. the cup shuffling seem to have been "staged". The end results are correct, but the method of getting them is nowhere near as fluid and elegant as in the demo. They used a series of still images with carefully crafted prompts. More info: https://developers.googleblog.com/2023/12/how-its-made-gemin...
Everyone fudges demo's, but does seem like Google fumbles them, they backfire.
When Bard 'hallucinates', their stock tanks.
When GPT 'hallucinates', it's all good.
This latest fumble does look pretty bad. A fudge to far.
Re: Gemini AI
#987Very impressive! I noticed two really notable things right off the bat: 1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub i…
Those impressive demos, e.g. the cup shuffling seem to have been "staged". The end results are correct, but the method of getting them is nowhere near as fluid and elegant as in the demo. They used a series of still images with carefully crafted prompts. More info: https://developers.googleblog.com/2023/12/how-its-made-gemin...
You don't seem to be responding to my post. I talked about two things I prompted Bard with, not the video.
Re: Gemini AI
#988Lots of comments about it barely beating GPT-4 despite the latter being out for a while, but personally ill be happy to have another alternative, if nothing else for the competition. But I really dislike these pre-availability announcements - we have to speculate and take their benchmarks for gospel for a week, while they get a bunch of press for unproven claims. Back to the original point though, ill be happier havi…
I've found Claude.ai to provide better responses than chatgpt 4 in the project planning arena (user stories, test cases, etc.)
Re: Gemini AI
#989It is just fake https://www.techradar.com/computing/artificial-intelligence/...
Re: Gemini AI
#990Very impressive! I noticed two really notable things right off the bat: 1. I asked it a question about a feature that TypeScript doesn't have[1]. GPT4 usually does not recognize that it's impossible (I've tried asking it a bunch of times, it gets it right with like 50% probability) and hallucinates an answer. Gemini correctly says that it's impossible. The impressive thing was that it then linked to the open GitHub i…
> Does Gemini have a date cutoff at all? You can ask it. Here's what it responded with: > "Do you mean to ask if I have a cutoff date for the data I was trained on? If so, the answer is yes. My training data includes text and code from various sources, and the most recent data I was trained on was from July 2023."
Is that true, though? I wouldn't trust anything an AI told me without verifying it elsewhere first.