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

131–140 of 1001 posts

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

#131

Post by tomasff »

ipsum2 wrote: post #129
diggan wrote: post #113

Earlier quoted context omitted.

With some additional guidance and prompting to GPT4 on ChatGPT I've gotten it to at least output the correct solution sometimes (7 correct answers out of 10 tries): Find the correct answer to this riddle: > 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? Employ the following strategy: - Suggest a list of 5…

Great prompt. GPT-4 was able to answer this, but Gemini Ultra was not: Jake likes coke but not pepsi. He likes corn but not popcorn, and he likes pens but not pencils. Will Jake like salmon or cheese?

Gemini Ultra answered this correctly for me: " It's impossible to say for sure if Jake will like salmon or cheese based on the information given."

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

#133

Post by frabcus »

dobladov wrote: post #121
dobladov wrote: post #119

I would be willing to pay for an AI that it's not constantly worrying about my safety and ethics, it's very frustrating that even when I ask for tech related topics, Gemini it's holding information on the basis of actions that might cause harm to my devices.

As expected, I asked the same questions to perplexity.ai, and it gave a correct response, just with a minor disclaimer at the end explaining the risks.

What are some specific tech examples where Gemini won't answer?

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

#134

Post by mjgeddes »

hackerlight wrote: post #81
mjgeddes wrote: post #71

Earlier quoted context omitted.

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?

I usually put a couple of keywords in brackets at the beginning (before the body of the prompt) to provide some context

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

#135

Post by svat »

Palmik wrote: post #127

This is a dupe, see here for more discussion https://news.ycombinator.com/item?id=39300679

That submission was a link to the (uninformative) signup page, and the discussion is mostly about the link being uninformative and/or not working. This one is at least an announcement :)

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

#136

Post by ipsum2 »

tomasff wrote: post #131
ipsum2 wrote: post #129

Earlier quoted context omitted.

Great prompt. GPT-4 was able to answer this, but Gemini Ultra was not: Jake likes coke but not pepsi. He likes corn but not popcorn, and he likes pens but not pencils. Will Jake like salmon or cheese?

Gemini Ultra answered this correctly for me: " It's impossible to say for sure if Jake will like salmon or cheese based on the information given."

While technically true, you could say that about all riddles. See GPT-4's explanation here, which intuits the rule and answers the riddle correctly. https://chat.openai.com/share/b1452950-b493-4e27-b097-e64f21...

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

#137

Post by motoboi »

TechRemarker wrote: post #50
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....

Google Work Paying users always get the short end of the stick.

As always I feel stupid for giving google my money.

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

#138

Post by edu_do_cerrado »

I heavily use Chat GPT's API in my day job, as it is the core of our business (Ai-powered startup). When Gemini Pro launched, me and my team tested it in the same day for our product, but we where disappointed as it is was a bit worse than gpt 3.5 (at least in the same prompts that we already had). I really hope that Gemini Ultra surpass gpt4, it is always exciting to see and use new advanced tech, but I'm still a little skeptical about it, since Pro wasn't that great...
Post reply on HN