News for hackers. Stuff that matters.
Re:Bard’s latest update: more features, languages and countries by visarga on Thursday July 13, 2023 @10:54AM (#36710162)
I tried Bard and it feels worse than GPT-4, it doesn't follow the prompt very well. Uploading an invoice it failed to extract data, instead it responded with hallucinations.
Re:Bard’s latest update: more features, languages and countries by jug on Thursday July 13, 2023 @10:56AM (#36710188)
Yes, I think it should be compared to GPT 3.5. Google doesn't really have a public contender to GPT 4 yet but this is what the Gemini project is intended to be, by the newly formed/reformed Google DeepMind team.
Re:Bard’s latest update: more features, languages and countries by heliophobicdude on Thursday July 13, 2023 @11:39AM (#36710975)
I'm really excited about Gemini. It's supposed to have some sort of planning and problem solving ability[2][3]. If it is like Tree of Thoughts [1], then I'm so hyped!

Also take a peek at which institution most of the ToT authors are at.

1: https://arxiv.org/pdf/2305.10601.pdf 2: https://blog.google/technology/ai/google-io-2023-keynote-sun... 3: https://www.wired.com/story/google-deepmind-demis-hassabis-c...

Re:Bard’s latest update: more features, languages and countries by ilaksh on Thursday July 13, 2023 @12:21PM (#36711727)
When is Gemini going to be available?
Re:Bard’s latest update: more features, languages and countries by heliophobicdude on Thursday July 13, 2023 @12:28PM (#36711859)
Wired article said development will take a number of months. Perhaps we shall ask Barb?
Re:Bard’s latest update: more features, languages and countries by mrtranscendence on Friday July 14, 2023 @01:10PM (#36726800)
Who’s Barb? The only Barb I know is a retired greyhound breeder, and I doubt she knows.
Re:Bard’s latest update: more features, languages and countries by Xplune13 on Thursday July 13, 2023 @11:25AM (#36710702)
I don't think Bard can even perform at GPT 3.5 level, at least, not in my experience. Bard hallucinates pretty bad and you can't really be sure whether it's correct or not. Now, that's a given with any LLM, but in my experience, Bard usually gives you at least 1 wrong sentence in any of the results it produces whereas GPT 3.5 is mostly correct at surface level questions, but tends to hallucinate if you try to dig in deeper.

But, Bard can give you images as an output as well with the links to those images which may or may not be the correct links and GPT 3.5 can't do that. Still, in any general case, I'd say GPT 3.5 is way more reliable than Bard.

Re:Bard’s latest update: more features, languages and countries by xp84 on Thursday July 13, 2023 @11:11AM (#36710459)
It may be 3.5-like, however when I tried it, it seems like it has a lot more handcuffs applied for “safety,” and I don’t mean safety from Skynet and Terminators. I mean things like it refuses to speculate about what medical condition might cause some given symptoms. “Sorry, I’m just a language model.” GPT had no problem giving it an educated guess.

I personally find this type of “safety“ to be patronizing and insulting, but I’m sure there are people who would prefer government regulation banning the use of language models for various and sundry “inappropriate” questions in order to protect humans who have no common sense. Anyway, in this condition, Bard’s a no for me.

Re:Bard’s latest update: more features, languages and countries by mrtranscendence on Friday July 14, 2023 @01:12PM (#36726837)
> I mean things like it refuses to speculate about what medical condition might cause some given symptoms.

Are you sure about this specifically? I’ve recently had zero trouble getting GPT-4 to give potential diagnoses for a given set of symptoms, though perhaps it’s an issue of prompting.

Re:Bard’s latest update: more features, languages and countries by dwaltrip on Thursday July 13, 2023 @01:34PM (#36712952)
Bard seems worse than gpt-3.5 in my experience.