Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

blog.google

Post reply on HN
Print view View original

81–90 of 1001 posts

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#81

Post by hackerlight »

mjgeddes wrote: post #71
codekaze wrote: post #64

Just played with Gemini Ultra for like 10-15 mins, and right off the bat, it made mistakes I've never seen GPT-4 do. To give you an example, I asked Gemini Ultra how to set up a real-time system for a TikTok-like feed that matches card difficulty with user ability. It correctly mentioned "Item Response Theory (IRT)", which was a good start. But when I followed up asking how to implement a real-time IRT system, it sud…

Yeah, I noticed with 'Gemini Pro' , it didn't seem to be able to remember much about earlier outputs in the conversation (apparently little to no context window), which obviously drastically dumbs it down. I was starting to get OK results with 'Pro', but I had to use special prompting tricks. Tried 'Advanced' (Ultra), seems only marginally better so far.

> I was starting to get OK results with 'Pro', but I had to use special prompting tricks.

Like what?

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#82

Post by ipsum2 »

In the 20 minutes of experimentation, I'm really impressed with the quality of Bard Advanced (Gemini Ultra). The results are as good as GPT-4, and in some cases is better. So far:

pros:

- better at translation (tried Chinese and Japanese idioms to English)

- better at incorporating search results in its answer vs gpt-4 bing

cons:

- slightly worse at coding

- censorship is more annoying (have to ask multiple times about medical topics)

- Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out)

- Hallucinates a lot when asked to describe an image

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#83

Post by alphabetting »

Gemini Ultra seems better on logic than GPT4. Still messing around testing but here's a prompt Ultra nailed but GPT4 completely botched:

Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears

https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#84

Post by tomasff »

alphabetting wrote: post #83

Gemini Ultra seems better on logic than GPT4. Still messing around testing but here's a prompt Ultra nailed but GPT4 completely botched: Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png

Is image generation working for you?

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#85

Post by Zenst »

Wow, I pay £1.50 currently, which is paid nicely via google rewards every month for a year, ticks along nicely. A £18.99/month bolt-on, nope, if couple quid, sure, but just priced out and what I would call top-end whale marketing price farming, which down the line will, I predict - half before years out at least.

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#86

Post by codekaze »

tomasff wrote: post #84
alphabetting wrote: post #83

Gemini Ultra seems better on logic than GPT4. Still messing around testing but here's a prompt Ultra nailed but GPT4 completely botched: Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png

Is image generation working for you?

It's working for me (on Gemini Advanced)

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#87

Post by alphabetting »

tomasff wrote: post #84
alphabetting wrote: post #83

Gemini Ultra seems better on logic than GPT4. Still messing around testing but here's a prompt Ultra nailed but GPT4 completely botched: Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png

Is image generation working for you?

Yeah. I don't have much personal use for image generation though.

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#88

Post by sebtron »

dorianmariefr wrote: post #5

"Sorry, Gemini Advanced isn't available for you" "Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age." Learn more: https://login.corp.google.com/request?s=support.corp.google....

"Please sign in your Google account"

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#89

Post by neel8986 »

alphabetting wrote: post #83

Gemini Ultra seems better on logic than GPT4. Still messing around testing but here's a prompt Ultra nailed but GPT4 completely botched: Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png

Wow. Is this a puzzle from internet. I could have never guessed the answer

Re: Bard is now Gemini, and we’re rolling out a mobile app and Gemini Advanced

#90

Post by adr1an »

nazgul17 wrote: post #77
nolok wrote: post #51

Earlier quoted context omitted.

If you use any cloud storage, including others like dropbox or icloud, you must always assume that. Whether you're a business or an individual.

No, you would assign a probability to the event. And that probability would be higher for a Google product.

That might be selection bias, the news posted here are only newsworthy because it's Google. Anyhow, I trust smaller shops a bit more than big corps (no matter the product or service being purchased), but it's subjective. In regards to tech, I trust myself first. In the same way that a Chef might not prefer going to any common restaurant, sure.
Post reply on HN