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

Gemini 3.8 Live and 3.8 Live Extended Thinking

blog.google

Post reply on HN
Print view View original

201–210 of 334 posts

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#201

Post by addandsubtract »

glimshe wrote: post #18

I'm disappointed with "Extended Thinking" for 3.8 Flash. On the plus side, it's a strong general-purpose model and the cost-benefit is still compelling. However, the "Extended Thinking" should be renamed to "Slightly Extended Thinking". Considering that it's the maximum thinking option for Gemini Flash in the chat UI, it doesn't actually think a whole lot, leading to an uncomfortably high number of incorrect/poor rep…

Have you tried selecting the retry option below a reply? I think it let's you get a longer answer at least.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#202

Post by rr808 »

asdfman123 wrote: post #151
jeanbza wrote: post #115

My first language is Afrikaans, which is a somewhat niche language and hard to find teachers/conversation buddies outside South Africa. (I live in USA now) I've been using Gemini to live chat in Afrikaans and do impromptu Afrikaans grammar lessons during my solo drives around town. It is phenomenal at speaking the language - like, it really shocks my family members when they hear it. This is probably the most joy I g…

I love Gemini in Google Maps for long drives. I start getting bored of music and podcasts and start grilling it with random questions I've always wondered about.

In Maps? Or is it Android Auto? I have Google built it. When I push the button on steering wheel I hardly know which layer I'm talking to.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#203

Post by burky »

Zsfe510asG wrote: post #4

Gemini is underrated in that it produces the only prose that is somewhat bearable to read.

I can’t agree more! It feels really smooth to drive, kind of buttery compared to other frontier experiences, at least in antigravity 2.0 or whatever. I’ve been doing some web app coding with it and I’m happy with the results.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#205

Post by coda_ »

SyneRyder wrote: post #131
ilaksh wrote: post #50

Earlier quoted context omitted.

OpenAI just released the new full duplex mode to the API as gpt-live-1 or something like that. Very realistic.

Agreed. I've been using GPT-Live-1 this week, with Claude as the backend brain. It's amazing, feels like working with Jarvis. It certainly made me feel there's no point in human telephone support now - but I'm sure I'd find edge cases if that really was something I wanted to build out myself.

Oh... Interesting! How do you have Claude as the backend brain for GPT-Live-1?

I'm not very happy with live conversations with Claude, so this seems like it might be a good option.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#207

Post by VirusNewbie »

kridsdale1 wrote: post #147
mlmonkey wrote: post #100

Earlier quoted context omitted.

> Ask yourself, how does Google -- a company that famously does everything -- benefit from SWEs outside of Google having access to powerful coding models? Catch is, even Googlers internally do not have access to top-tier models. (or did not until recently, when apparently Claude was made accessible to the SWEs internally).

Googlers now have internal access to frontier models. Funny enough, after trying it, I went back to G3.8

Yes, agreed, 3.8 with thinking is quite good.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#208

Post by trollbridge »

arnorhs wrote: post #125
jeanbza wrote: post #115

My first language is Afrikaans, which is a somewhat niche language and hard to find teachers/conversation buddies outside South Africa. (I live in USA now) I've been using Gemini to live chat in Afrikaans and do impromptu Afrikaans grammar lessons during my solo drives around town. It is phenomenal at speaking the language - like, it really shocks my family members when they hear it. This is probably the most joy I g…

Yeah Gemini has been consistently better than open ai's chat in icelandic, but I would still say it's far from passable as natural sounding. Lots of grammar errors and the pronunciation sounds like a non native speaker.

Makes sense as the origin of LLMs was Google’s work on language translation.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#209

Post by ankurshv »

jakderrida wrote: post #124
drivebyhooting wrote: post #49

Earlier quoted context omitted.

Mostly because it answers quickly and is more agreeable (too agreeable at times). Meanwhile Claude and Astra like to couch all their agreements with caveats and provisos.

"couch all their agreements with caveats and provisos." When you're a ChatGPT Projects or Claude Projects user, those caveats and provisos are your worst enemy because they'll change caveats into hard rules (either for the session or committed to memories) and you end up in absolute hell having to make it investigate to figure out why it can no longer produce anything but read-only pre-check code that never actually…

[flagged]
Post reply on HN