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

301–310 of 335 posts

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#301

Post by NorthSouthNorth »

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…

Lekker man. Although I speak it often, I could use an LLM to help me progress as I've been stuck at my current level for about a year and typing it is not something I enjoy.

I find no greater joy than listening to a TTS model say Poes (Google translate is one of the funnier ones to make swear). Reminds me of being 14 lol.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#302

Post by popcorncowboy »

YoumuChan wrote: post #212
asdfman123 wrote: post #155

Earlier quoted context omitted.

I work for Google and we have the choice between Gemini models and Opus. Opus is slightly better than Gemini flash but I find the style unbearable. It reminds me of a pedantic grad student.

Not only that, Opus likes to invent arcane jargons. And the longer the task runs, the harder it is to understand its output. The conversation will be filled with uncommon word choices and awkward sentence structure.

"Watermarking"

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#303

Post by popcorncowboy »

chpatrick wrote: post #62
Zsfe510asG wrote: post #4

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

I find its style the most sycophantic and annoying personally.

Never has it been brought so clearly into light how brilliant I am, than in correspondence with Gemini.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#304

Post by ha-shine »

The voices sound really pleasant and realistic. Sadly it doesn't support SIP. I found forwarding streams with websocket for phone calls tend to introduce some unwanted latency that's quite noticeable in a conversation. I've found a lot of success with GPT-live-1 so far, but the generated voices are lacking something I can't put my finger on.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#305

Post by orsenthil »

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 am assuming these languages are present in translate.google.com If Google Gemini is good in languages other than English, while other models are not, then we can trace back it back to the translate.google.com as a resource as one possibility.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#307

Post by artdigital »

yoavm wrote: post #280
artdigital wrote: post #257

Even if really great, it still can’t use tools. The only consumer Google thing with access to MCP tools is Gemini Spark and that has lots of other problems. I wish they would combine their efforts on a great consumer product but it’s Google we’re talking about… I still dream of the day that we get full tool parity in voice and text mode so your voice assistant can do everything you connect for you. Grok and Claude ar…

Note sure what you mean by "tools". It does support function calling, so you can hook it to whatever tools you want. I'm using it with Home Assistant to control my smart home devices.

I mean the consumer Gemini app. It has no way to connect MCP servers to it. Only Spark can, if you switch your Gemini to the separate Spark mode

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#308

Post by mncharity »

normie3000 wrote: post #239
mncharity wrote: post #234

Earlier quoted context omitted.

Fwiw, it's been very easy to nudge Qwen 27B/35B to think in Chinese. No need for prefills like "思考：" ("Think:") or such. Relatedly, when chatting with frontier models about science education content design, I've found it very helpful to mix in Chinese education terms. In English, for example, NGSS is such a massive attractor, discussing nearby topics often yields NGSS "slop". And "estimation" (educational) in the US…

This is an interesting post, but as a non-American it's hard to understand what's it's alluding to in some parts. The one criticism of NGSS I found from a quick skim of https://en.wikipedia.org/wiki/Next_Generation_Science_Standa... is that it teaches evolution. What does "estimation" mean in the US?!

> What does "estimation" mean in the US?!

"Estimation" as a skill in US education, primary school on, is pervasively about point estimates - single numbers. Bounding, a range of safe/reasonable/likely/possible numbers, is very rare. In Fermi questions/problems also.

Even in such goodness as Sanjoy Mahajan's Art of Insight and Street-Fighting[1]... the only only "bound" mentioned is "Printed and bound in [USA]", and there is no "round".[2]

In contrast, IIUC, China is pervasively about "Da Gu" and "Xiao Gu", "round up" and "round down". Point estimates are secondary. Lower and upper bounds are apparently even a cultural concept: an individual's degree vs capability/fate; policy equity vs excellence; economic targets.

In education, my understanding is point estimates have much poorer conversational/collaborative dynamics than range estimates. Bounding lends itself to incremental collaboration. "Can anyone suggest another low or high bound?". Discussions around point estimates seem usually merely about the collection of individual estimates.

> NGSS

Ah, NGSS isn't bad particularly. I meant that discussion/mention of NGSS appears so very much in English training data, that AI chat on topics related to NGSS seem to draw regurgitations of NGSS. AI "slop" in the sense that "ignore NGSS, just reason from a superset of its underlying concepts"... isn't an LLM strength.

> hard to understand

Sorry - Thanks for asking!

[1] open access: https://direct.mit.edu/books/oa-monograph/5345/The-Art-of-In... https://direct.mit.edu/books/oa-monograph/5339/Street-Fighti... [2] search "bound": https://www.google.com/books/edition/The_Art_of_Insight_in_S... https://www.google.com/books/edition/Street_Fighting_Mathema...

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#309

Post by mncharity »

eru wrote: post #236
mncharity wrote: post #234

Earlier quoted context omitted.

Fwiw, it's been very easy to nudge Qwen 27B/35B to think in Chinese. No need for prefills like "思考：" ("Think:") or such. Relatedly, when chatting with frontier models about science education content design, I've found it very helpful to mix in Chinese education terms. In English, for example, NGSS is such a massive attractor, discussing nearby topics often yields NGSS "slop". And "estimation" (educational) in the US…

> In English, for example, NGSS is such a massive attractor, discussing nearby topics often yields NGSS "slop". For that particular attractor, even German or Spanish or so might help avoid it? Or perhaps even just using British English?

Oh, good point! Something to check. I've been thinking of Chinese as a strength of Chinese models, but other languages might be sufficient here.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#310

Post by mattstir »

ha-shine wrote: post #304

The voices sound really pleasant and realistic. Sadly it doesn't support SIP. I found forwarding streams with websocket for phone calls tend to introduce some unwanted latency that's quite noticeable in a conversation. I've found a lot of success with GPT-live-1 so far, but the generated voices are lacking something I can't put my finger on.

What's your use-case for automating phone calls?
Post reply on HN