Gemini 3.8 Flash and 3.8 Flash Cyber • Hacker News Board

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#381

Post by ChickeNES » Wed, Sep 02, 2026, 7:14 PM UTC

simonw wrote: post #310

superze wrote: post #290

Earlier quoted context omitted.

Yes, very imaginary to think that the code comes from pretrained data and copy pasting whole blocks. It's not like this is exactly how LLMs work.

Are you a frequent user of LLMs? That "copy pasting whole blocks" mental model doesn't hold up to regular usage, in my opinion.

They probably saw that report years ago of copilot dumping out the fast inverse sqrt function, and assume that's all they can do. From experience most anti-LLM people have either never used them, or used them back in the 3.5-4 era and then never again, though you might have even more experience with those people than I do. :P

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#382

Post by satvikpendem » Wed, Sep 02, 2026, 7:16 PM UTC

stwrt wrote: post #78

satvikpendem wrote: post #43

Is the Gemini CLI still terrible compared to Claude Code and Codex? The harness the main thing holding back Google models as they could've been the best given all the advantages in compute capacity and training data they initially had, where now even the Google CEO said they're falling behind in agentic tasks, which is sort of a vicious cycle because RLHF relies on human usage.

In May they replaced the Gemini CLI with the Antigravity CLI. https://developers.googleblog.com/an-important-update-transi...

That's what I meant sorry. I used that one too and it still wasn't as good as competitors.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#383

Post by _puk » Wed, Sep 02, 2026, 7:17 PM UTC

WarmWash wrote: post #138

world2vec wrote: post #88

Earlier quoted context omitted.

The labs are clearly training for the benchmark.

This has been addressed endlessly, for a few years now, and is just as much of a trope as "this benchmark is useless".

https://news.ycombinator.com/item?id=49538267

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#384

Post by fc417fc802 » Wed, Sep 02, 2026, 7:17 PM UTC

BeetleB wrote: post #171

dymk wrote: post #130

Earlier quoted context omitted.

you didn’t even read your comment before you posted it?

1. That's a wild conclusion from his comment! Understand that it's not an "either/or". 2. I'd wager the majority of HN commenters don't read their own comment before posting (pre-LLM days).

I can read my own comment twice over and still somehow miss seemingly obvious wording errors.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#385

Post by exacube » Wed, Sep 02, 2026, 7:20 PM UTC

pwython wrote: post #34

Is there any reason to even use 3.1 Pro now?

IME 3.1 Pro still has better system-instruction following than Flash 3.7, esp. when there're many conditions and clauses. 3.1 also writes better prose for technical material than Flash 3.7.

Once the system prompt complexity goes up, Flash starts to write very dense english. it might be fine for tasks like coding, but not for user-facing text meant to be digested by the average person.

I haven't tested 3.8 on my workload yet.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#386

Post by firemelt » Wed, Sep 02, 2026, 7:20 PM UTC

I wish google to thrive

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#387

Post by cogman10 » Wed, Sep 02, 2026, 7:20 PM UTC

ddp26 wrote: post #379

There must be a deeper read on why Google can rapidly ship better small models while being delayed months on the bigger model. What's the simplest explanation?

Perhaps post training? I believe I read that Qwen 3.8 is just post trained Qwen 3.6, which is why it was able to be released so quick.

It may be that these flash models are simply post trained larger older models.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#388

Post by whateveracct » Wed, Sep 02, 2026, 7:23 PM UTC

sawjet wrote: post #277

wayeq wrote: post #260

Earlier quoted context omitted.

> That's both cool and fast. and probably a barely modified knock-off of some github project that it trained on

You're so upset that you have to invent an imaginary hypothesis to make yourself feel better.

they're wrong but they are right that this isn't interesting

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#389

Post by HarHarVeryFunny » Wed, Sep 02, 2026, 7:23 PM UTC

shuvrojit wrote: post #31

Gemini is getting less useful with each update. I could edit a pdf with the 3-pro model before but 3.1-pro couldn't edit the given pdf nor it could generate one for me.

If you want to "edit" a PDF, then Claude Sonnet works well, although what it's going to do is regenerate it from scratch trying to retain overall formatting. It can even do this for scanned PDFs and foreign language ones that need translating.

If you just need to create PDFs, not edit them, then Gemini notebook (notebook.google) works well and has Google's usual very high free usage limits.

AFAIK in general you can't really edit PDFs since it's not a reflowable format - even with Adobe tools all that editing does is modify the text within a text box - not reflow the document to adjust to any change in size of the text box.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#390

Post by watusername » Wed, Sep 02, 2026, 7:27 PM UTC

_aavaa_ wrote: post #366

brap wrote: post #318

Earlier quoted context omitted.

Antigravity has been also rapidly improving lately, and your can also use any of the open coding harnesses. But I mostly meant “harness” as in your workflow/loop setup.

Do they officially support you using your subscription in other harnesses?

No, and Google actively bans people for using their subscription from other harnesses via various proxies/gateways.

To preempt certain replies, yes, I know you can pay API prices and use whatever harness you want.