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

261–270 of 334 posts

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#261

Post by otabdeveloper4 »

Gareth321 wrote: post #244
galkk wrote: post #231

I don’t understand good experiences people are having with Gemini. It’s the only model that sometimes loses/forgets context in literally next message. Plus feeding unasked product links to responses.

I strongly agree. I suspect it's people who have not yet used the paid models from OpenAI and Anthropic. Gemini is comparable to free models from other providers, but not in the same universe as paid models. This is frustrating because when I discuss AI with laypeople they think it's still incapable of counting the number of Rs in "strawberry." They believe it to be essentially useless and incapable of basic tasks. W…

> you're just not using the latest model, bro

Pro tip, ChatGPT is the normiest of all normie websites right now. You're not part of the cognoscenti just because you learned how to type prompts into one of the most popular websites in the world.

P.S. You're probably not using OpenAI models for complex or non-standard tasks. It shits the best just as often as Qwen when you need precision and detail in a non-obvious problem.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#262

Post by w4yai »

galkk wrote: post #231

I don’t understand good experiences people are having with Gemini. It’s the only model that sometimes loses/forgets context in literally next message. Plus feeding unasked product links to responses.

Have you tried Gemini 3.8 Flash recently ?

I was like you before, Gemini was the worst model to me.

Then 3.8 came out. At first I was sceptical, but this model *is* able to do useful things ! Complex things.

Of course, it is NOT perfect. But for things like small/medium complex tasks subagents, it's perfect.

Now, is it worth the money vs Astra ? I don't think so. But still my point remain relevant.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#265

Post by belowavgiq »

otabdeveloper4 wrote: post #261
Gareth321 wrote: post #244

Earlier quoted context omitted.

I strongly agree. I suspect it's people who have not yet used the paid models from OpenAI and Anthropic. Gemini is comparable to free models from other providers, but not in the same universe as paid models. This is frustrating because when I discuss AI with laypeople they think it's still incapable of counting the number of Rs in "strawberry." They believe it to be essentially useless and incapable of basic tasks. W…

> you're just not using the latest model, bro Pro tip, ChatGPT is the normiest of all normie websites right now. You're not part of the cognoscenti just because you learned how to type prompts into one of the most popular websites in the world. P.S. You're probably not using OpenAI models for complex or non-standard tasks. It shits the best just as often as Qwen when you need precision and detail in a non-obvious pro…

Where did he claim otherwise?

Take your meds.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#266

Post by aktau »

FranzFerdiNaN wrote: post #259
3stacks wrote: post #167

Earlier quoted context omitted.

My father-in-law was saying the same thing about Gemini 12 months ago regarding the Afrikaans speech. I've tried a few of them in my studies but none of them could seem to switch between English/Afrikaans except Gemini. It's an interesting time to be a language learner As jy wil, ons kan saam praat op Discord :) maar my Afrikaans is sleg

As a Dutch person i find Afrikaans always interesting whenever i happen to encounter it in the wild. As if a common ancestor took a very different evolutionary path.

Given that Dutch is the ancestor here (not that Dutch hasn't changed since the split), I wouldn't call it "as if".

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#267

Post by FranzFerdiNaN »

asdfman123 wrote: post #155
Zsfe510asG wrote: post #4

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

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.

The 4.5 models were the last Anthropic models that were actually pleasant to read. Especially Sonnet 4.5 was really fun to use for non-coding purposes. I liked having it generate silly short stories while waiting for deployments to finish. Haiku 4.5 still has a small bit of that charm, but 4.6 and later models are all unbearable unless you want a simple 'this is the answer' to a question.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#268

Post by TacticalCoder »

Gareth321 wrote: post #244
galkk wrote: post #231

I don’t understand good experiences people are having with Gemini. It’s the only model that sometimes loses/forgets context in literally next message. Plus feeding unasked product links to responses.

I strongly agree. I suspect it's people who have not yet used the paid models from OpenAI and Anthropic. Gemini is comparable to free models from other providers, but not in the same universe as paid models. This is frustrating because when I discuss AI with laypeople they think it's still incapable of counting the number of Rs in "strawberry." They believe it to be essentially useless and incapable of basic tasks. W…

> I suspect it's people who have not yet used the paid models from OpenAI and Anthropic. Gemini is comparable to free models from other providers, but not in the same universe as paid models.

I totally disagree. I pay for both ChatGPT and Anthropic (haven't tried the chinese models yet) and yet Gemini is my go-to model (and I pay for it too through Google Workspace subscriptions for several domain names tied to Google/GMail) for anything that is not coding.

I find Gemini better/quicker/more polished for basically every single subject out there that is not "write me lines of code".

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#269

Post by TacticalCoder »

whateveracct wrote: post #254
galkk wrote: post #231

I don’t understand good experiences people are having with Gemini. It’s the only model that sometimes loses/forgets context in literally next message. Plus feeding unasked product links to responses.

i have programmed a dozen scripts with google search AI lol they'll live in my rc for decades

Ah yup for quick one-off one-liners or small Bash script, Gemini works perfectly fine too. For longer scripts I use another model.

Re: Gemini 3.8 Live and 3.8 Live Extended Thinking

#270

Post by Gareth321 »

otabdeveloper4 wrote: post #261
Gareth321 wrote: post #244

Earlier quoted context omitted.

I strongly agree. I suspect it's people who have not yet used the paid models from OpenAI and Anthropic. Gemini is comparable to free models from other providers, but not in the same universe as paid models. This is frustrating because when I discuss AI with laypeople they think it's still incapable of counting the number of Rs in "strawberry." They believe it to be essentially useless and incapable of basic tasks. W…

> you're just not using the latest model, bro Pro tip, ChatGPT is the normiest of all normie websites right now. You're not part of the cognoscenti just because you learned how to type prompts into one of the most popular websites in the world. P.S. You're probably not using OpenAI models for complex or non-standard tasks. It shits the best just as often as Qwen when you need precision and detail in a non-obvious pro…

> You're probably not using OpenAI models for complex or non-standard tasks. It shits the best just as often as Qwen when you need precision and detail in a non-obvious problem.

The benchmarks clearly show otherwise. This is your cue to tell me the benchmarks are made by the Illuminati and only your superior and subjective methods of evaluation are correct.

Post reply on HN