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

PaLM 2 Technical Report [pdf]

ai.google

Post reply on HN
Print view View original

231–240 of 297 posts

Re: PaLM 2 Technical Report [pdf]

#231

Post by mirekrusin »

shrimpx wrote: post #162
stygiansonic wrote: post #143

Earlier quoted context omitted.

In that sense, it's very similar to the GPT-4 Technical Report. The era of being "open" about LLMs or other "secret sauce" models in published papers may be over, since these things have become existential threats to companies.

Btw I've arrived at a different interpretation of the "Open" in OpenAI. It's open in the sense that the generic LLM is exposed via an API, allowing companies to build anything they want on top. Companies like Google have been working on language models (and AI more broadly) for years but have hid the generic intelligence of their models, exposing it only via improvements to their products. OpenAI bucked this trend an…

It’s “open” as in “open for business”.

Re: PaLM 2 Technical Report [pdf]

#232

Post by ivalm »

gekoxyz wrote: post #84
jp42 wrote: post #62

personal experience - I'm using GPT4 for writing code especially in python. After using bard today, I feel bard is doing quite well considering its free. I will keep using it and if its keep doing well, I will cancel GPT4 $20/month subscription.

why don't you just use chatGPT? from what i know it's running GPT3.5 and it's not that different (at least in terms of code quality)

As someone writing my first meaningful react app, code quality from gpt4 is monstrously better than 3.5. With gpt 4 i can often paste entire components and get meaningful corrections/bug fixes/non-trivial refactors. 3.5 just does a loop of mistaken fixes while it runs out of context length.

Re: PaLM 2 Technical Report [pdf]

#233

Post by robertlagrant »

adastra22 wrote: post #170
ftxbro wrote: post #169

Earlier quoted context omitted.

> Btw I've arrived at a different interpretation of the "Open" in OpenAI. I don't understand why people have to keep trying to wrap their head around the word 'Open' in OpenAI. If you ever saw a commercial like a product has a 'great new taste' but then you tried it and it tasted bad, would you twist yourself into knots trying to understand how you went wrong in your interpretation of 'great'? No that's ridiculous. S…

You mean when they filled out a form to incorporate their non-profit. Which they later turned into a for-profit company after reaping all the goodwill. The “Open” used to mean something.

> Which they later turned into a for-profit company after reaping all the goodwill

Did they have a lot of goodwill attached to their company? What did that give them?

Re: PaLM 2 Technical Report [pdf]

#234

Post by rkwasny »

ilaksh wrote: post #212

Here is their Chat Playground for PaLM 2 https://console.cloud.google.com/vertex-ai/generative/langua... (you have to be logged in to Google Cloud Console I think) Anyone know what parameters are best for code generation? I tried something simple for Node.js and it wasn't horrible but not working. Maybe I used the wron parameters. I tried using 0 for the temperature and turning everything else down like I do with the…

Whoah it gives some seriously wrong answers to coding questions, to the point that they are dangerous!

I think we have to wait for the explanation is chat-bison PaLM 1 or 2

Re: PaLM 2 Technical Report [pdf]

#235

Post by ilitirit »

gekoxyz wrote: post #84
jp42 wrote: post #62

personal experience - I'm using GPT4 for writing code especially in python. After using bard today, I feel bard is doing quite well considering its free. I will keep using it and if its keep doing well, I will cancel GPT4 $20/month subscription.

why don't you just use chatGPT? from what i know it's running GPT3.5 and it's not that different (at least in terms of code quality)

There's a massive difference in response quality in my experience.

For example, I asked 3.5 to find a bug in a lengthy piece of Javascript. It said it's hard to give a correct answer because it doesn't know what the HTML or CSS looks like.

GPT4 spotted the bug almost immediately (it didn't manage to fix it though).

Re: PaLM 2 Technical Report [pdf]

#236

Post by KeplerBoy »

dmix wrote: post #183
KeplerBoy wrote: post #117

Earlier quoted context omitted.

You might be right. What a dystopian future that will be. Make a few requests too many and the webserver might think you're scraping data so it gaslights you into reading bullshit.

Is this sarcasm? I can’t tell.

It's not. The internet will be crazy once compute will be cheap enough to slightly modify all displayed content slightly to suit your personal user profile.

Re: PaLM 2 Technical Report [pdf]

#237

Post by mrinterweb »

adastra22 wrote: post #170
ftxbro wrote: post #169

Earlier quoted context omitted.

> Btw I've arrived at a different interpretation of the "Open" in OpenAI. I don't understand why people have to keep trying to wrap their head around the word 'Open' in OpenAI. If you ever saw a commercial like a product has a 'great new taste' but then you tried it and it tasted bad, would you twist yourself into knots trying to understand how you went wrong in your interpretation of 'great'? No that's ridiculous. S…

You mean when they filled out a form to incorporate their non-profit. Which they later turned into a for-profit company after reaping all the goodwill. The “Open” used to mean something.

"Open" means: "Open for business." Not sure how anyone could confuse that.

Re: PaLM 2 Technical Report [pdf]

#238

Post by eternalban »

shrimpx wrote: post #184
ftxbro wrote: post #169

Earlier quoted context omitted.

> Btw I've arrived at a different interpretation of the "Open" in OpenAI. I don't understand why people have to keep trying to wrap their head around the word 'Open' in OpenAI. If you ever saw a commercial like a product has a 'great new taste' but then you tried it and it tasted bad, would you twist yourself into knots trying to understand how you went wrong in your interpretation of 'great'? No that's ridiculous. S…

I think the strong connotation of the word "open" in the software community comes from "open source". If OSS was called "great new source" and a new closed source company called itself GreatNewAI you'd have a similar phenomenon of people taking apart the name.

'Open Systems' predate 'Open Source' by a decade.

https://en.wikipedia.org/wiki/Open_system_(computing)

https://en.wikipedia.org/wiki/The_Open_Group

Re: PaLM 2 Technical Report [pdf]

#239

Post by Jweb_Guru »

toxik wrote: post #218
fzliu wrote: post #140

I don't understand how this can be considered a technical report. No information on model architecture, distributed training methodology, or optimizations. The "Training dataset" section is a pathetic 0.5 pages long. Come on, Google.

Yeah, this is a holdover from where LLMs grew out of: academia. "Technical report" is what you reach for when you don't want to compare to actual competitive baselines.

I'm sorry, this is nonsense. Technical reports exist to fill in information that is useful for readers but not necessary to understand the key contributions of the work, and/or that don't fit within the journal or conference's page limit. I'm not sure where you got the idea that it is something people do to avoid competitive baselines; IME, the peer-reviewed portion of the publication is far more likely to contain misleading benchmarks than the technical report, since the paper is trying to "sell" the work in a way the technical report is not.

What this is an instance of is Google's approach to academic publishing of releasing a paper that contains almost no actionable information, but which is considered important and publishable solely because it came from Google and therefore is used in industry. This has been exhibited many times before--e.g. see the original Spanner paper, which was so light on details and confusing that they needed to release a followup paper several years later to explain what the system was even using the atomic clocks for!

Re: PaLM 2 Technical Report [pdf]

#240

Post by cowl »

vineyardmike wrote: post #223
Closi wrote: post #214

May be a weird takeaway, but I did find it strange how much the whole report focussed on misgendering as a safety issue. I agree it’s important to get right, but it seems like one of hundreds of safety/alignment issues and that many others are de-emphasised or ignored.

I didn't find it to be a particularly notable issue relative to the rest of the issues they mentioned. It didn't seem to be overrepresented to me... That said, it's something that is more controllable across languages. All people, in all languages, have a roughly equal distribution of genders, but not race/religion, etc. Japanese language text will have similar gender distributions to English, but likely not equal di…

I'm not sure you got the right example here. "è un dottore" in Italian is unambiguously a He. Italian Language is a gendered one and leaves little room for context interpretation. A female doctor would be 'una dottoressa" and you would never say it without a pronoun either so the full frase "lei è una dottoressa" does leave zero room for implying anything. Maybe your comment would be more valid in other languages that are not so strongly gendered.
Post reply on HN