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

561–570 of 1001 posts

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

#561

Post by maxwelljoslyn »

jstummbillig wrote: post #546
DannyBee wrote: post #386

Earlier quoted context omitted.

so I have done a lot of transcripts, coding, one versus the other (gpt4 vs ultra). Often simple prompts like refactor this code or convert this python to typescript. My experience is that Gemini ultra understands the code better, but doesn’t always give me as complete of results (they seem to limit output length more) Beyond that it is very smart. I’ve had to tell me this code packs 12 bit integers into different par…

> That said, I have fed thousands of lines of code into both of them and asked them to refactor it, and neither one of them made more than one error. All code otherwise compiled and worked first try. I would be very interested to get a more detailed scope of what you did here. Feeding thousands of lines of code into GPT4 and getting a near perfect refactor does very much NOT sound like my experience, but it seems hig…

Seconded. I am also keenly interested in learning more. It would be a great boon on my current project to be able to let the AI refactor mountains of legacy code (while taking steps to ensure the results are trustworthy and equivalent, of course.)

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

#562

Post by jonplackett »

eitally wrote: post #550
jonplackett wrote: post #526

Earlier quoted context omitted.

Better - but it has not understood the message is for the person on the other side. It thinks that it’s actually mirror writing intended to confer the opposite meaning than written. And then waffles of about door safety for ages.

Honestly, I don't see why this counts as the model getting things wrong, since in your prompt you don't specify which side of the door the text is printed on.

It’s a glass door! That’s the whole point of the question. You can see it from both sides.

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

#563

Post by abraxas »

jonplackett wrote: post #427

I’ve been pretty excited to finally try Gemini advanced. So far pretty disappointed. Here’s my go-to test question - which even chat gpt 3.5 can get. Question: I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why Gemini advanced: You should push the door. Here's why: * Mirror Writing: The word "PUSH" is written in mirror writing, meaning it would appear corr…

GPT-4:

> If the word "push" is written in mirror writing and you're facing it, it's likely that the message is intended for those on the opposite side of the door from you, meaning it's directed at people who are inside looking out. In this case, you should pull the door to open it. The mirror writing suggests that the instruction is not meant for your current position outside the door but for those inside, indicating the action they should take to open the door from their side.

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

#564

Post by Zetobal »

jimmyl02 wrote: post #553
bilalq wrote: post #547

> Your conversations are processed by human reviewers to improve the technologies powering Gemini Apps. Don’t enter anything you wouldn’t want reviewed or used. I appreciate them being upfront with that, but for a paid feature, it sucks that they offer no privacy or opt-out mechanism.

It seems like you can disable the data being used from training by turning off gemini app activity. > You can turn Gemini Apps Activity off If you don’t want future conversations reviewed or used to improve machine-learning models, turn off Gemini Apps Activity Opens in a new window .

And you can be sure it will reset with every update.

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

#565

Post by UncleOxidant »

ipsum2 wrote: post #82

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 abo…

I found it worse at coding than DeepSeek Coder on the couple of prompts I tried.

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

#566

Post by keenmaster »

jatins wrote: post #497
ipsum2 wrote: post #82

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 abo…

> - slightly worse at coding > - Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out) That takes most of my use cases. "logic" is what makes GPT often feel like AGI. Use cases like translation seem less impressive in comparison to logical reasoning because it feels like it's just something where you can throw a lot of data and it'll do better. While with logical reasoning i…

Exactly. That’s also why I find low parameter LLMs to be useless for me personally. I simply cannot trust anything that is so very illogical. GPT-4 is the first LLM that crossed into usable territory for me. Even GPT-3.5 was a fun toy and maybe good for summarization, but that’s it. It will be revolutionary when GPT-4 is cheap enough that thousands of calls don’t cost much. To imagine an LLM much smarter GPT-4…the future is bright.

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

#567

Post by mherrmann »

yandie wrote: post #549
jonplackett wrote: post #427

I’ve been pretty excited to finally try Gemini advanced. So far pretty disappointed. Here’s my go-to test question - which even chat gpt 3.5 can get. Question: I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why Gemini advanced: You should push the door. Here's why: * Mirror Writing: The word "PUSH" is written in mirror writing, meaning it would appear corr…

I got a different answer with GPT 3.5 > If the word "push" is written on the glass door in mirror writing, it means that from the other side of the door, it should be pushed. When you see the mirrored text from your side, it indicates the action to be taken from the opposite side. Therefore, in this scenario, you should push the door to open it.

So close!

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

#568

Post by jerbear4328 »

boppo1 wrote: post #542
andrewla wrote: post #513

Earlier quoted context omitted.

The amazing thing about emergent behavior in LLMs is that they are able to answer questions like these. I don't think it is completely understood how exactly they do this, but there's little doubt that they do.

Do you have any sources that prove this is true?

This looks pretty good to me:

https://chat.openai.com/share/040ac123-c690-4274-8216-6ae091...

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

#569

Post by 98codes »

bilalq wrote: post #547

> Your conversations are processed by human reviewers to improve the technologies powering Gemini Apps. Don’t enter anything you wouldn’t want reviewed or used. I appreciate them being upfront with that, but for a paid feature, it sucks that they offer no privacy or opt-out mechanism.

Well there's a line that the sales folks at Microsoft will bring out early & everywhere

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

#570

Post by nharada »

antonioevans wrote: post #147

I'm not impressed. When comparing Gemini/Bard to ChatGPT + GPTs, Bard/Gemini feel more like a search engine. I asked Gemini for help in planning a date with my date, who is famous enough that GPT4 knows her and her art. However, Gemini immediately started giving me step-by-step instructions to plan the date. I had to tell it to slow down and ask me questions first before giving an answer. It complied this time, but a…

"do you even have the embeddings for who I am??"
Post reply on HN