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

Gemini 3.8 Flash and 3.8 Flash Cyber

blog.google

Post reply on HN
Print view View original

491–500 of 699 posts

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#491

Post by brap »

sfink wrote: post #223

For my application, I'm still happily using gemini-2.5-flash and the only problem is when it reports being overloaded. It's for interpreting a downscaled phone camera photo of a hand-written shopping list on a whiteboard, and it works stunningly well. My handwriting sucks, too. (I guess the only relevance here is that if your problem matches a model's strengths, then you can do fine with a model that is several gener…

I believe the older models are being gradually phased out, newer ones have no availability issues

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#492

Post by thereitgoes456 »

2001zhaozhao wrote: post #341

How generous is the Google subscription quotas compared to Anthropic and OpenAI? This sounds like a really good potential model for high volume due to its speed and cost effectiveness. (By high volume I mean things like "main app just updated with XYZ commits, please scan XYZ plugins and surface any compatibility issues")

Really generous. I'm on the Pro plan and I just use Antigravity for vibe coding w/o automation. It's actually difficult to hit my weekly limit now, it takes about ~30-35 hours of continuous agent work, which virtually only happens when building a new app from scratch.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#493

Post by robertn702 »

pdimitar wrote: post #444
robertn702 wrote: post #391

Earlier quoted context omitted.

I highly recommend just getting out of Anthropic's (or anyone's) vendor lock-in. Use opencode or pi. You can still use your subscription pricing using a proxy. I switched to opencode and haven't looked back.

How do you do the proxy thing?

Meridian[0] for Claude Code, CLIProxyAPI[1] for everything else

[0] https://github.com/rynfar/meridian

[1] https://github.com/router-for-me/CLIProxyAPI

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#495

Post by simonw »

anigbrowl wrote: post #466
simonw wrote: post #64

Pelicans (thinking effort high, medium, low): https://tools.simonwillison.net/markdown-svg-renderer?url=ht... - high cost 8.9742 cents Here are the 3.7 pelicans for comparison: https://tools.simonwillison.net/markdown-svg-renderer.html?u... - high cost 8.4387 cents (I think thinking level low is a regression on 3.8 compared to 3.7.)

These are becoming unreadable as the reasoning chains expand. I think you should consider reformatting them and either putting the image first or else folding the COT output.

Yeah, putting reasoning in a details/summary is a good idea.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#496

Post by livinglist »

SchemaLoad wrote: post #484
adleyjulian wrote: post #296

Earlier quoted context omitted.

FYI in Chinese he/she/it all use the same pronoun "ta" when spoken.

They do have a separate character for animals and objects 它 vs 他/她, though I can imagine learning english and just learning ta = he.

There’s also one specifically for God - 祂, and one for animal - 牠, the first one you can see frequently in Chinese bibles or churches, the latter is rarely used.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#497

Post by simlevesque »

mvdtnz wrote: post #314
brap wrote: post #309

People have been sleeping on Gemini lately but these last few Flash releases (which were very rapid) are damn good. These sort of fast and cheap models are great for tasks that are verifiable and can be retried infinitely (like coding), you can basically get frontier results with a good harness (at a fraction of the time and money).

As someone who has stubbornly stuck with Claude Code, what's a good harness for Gemini models?

You can use any model with Claude Code. Most chinese one have a Anthropic compatible endpoint and for Google and OpenAI's models you can get a compatible endpoint with a proxy like Bifrost. No need to change your harness.

Re: Gemini 3.8 Flash and 3.8 Flash Cyber

#499

Post by NiloCK »

rahimnathwani wrote: post #133
jampa wrote: post #113

I've been using Gemini 3.7 for my personal trip planning app. Across multiple benchmarks, it ranks higher on everything I tried: - Real world knowledge (when a thing opens and closes, the geographic region, historical facts). It's also the best at taking a cluster of places and working out a visiting order. - Photo ranking (which photo should be the hero). Gemini can tell whether a photo is of the thing or of the vie…

One thing in your comment surprised me: "when a thing opens and closes" Why you would rely on the model's weights to know opening hours, instead of having the model call a web search tool to verify it on the official site?

Gemini models - at least via some interfaces - have tool calling API access to various Google integrations. flights.google.com, maps.google.com, etc.

The info isn't in the model weights.

Because of where I live, there are three viable airports for any given flight I might want to take, which historically has made shopping a real pain. But Gemini (and only Gemini) has greatly simplified it. Pramble plus date range plus destination and it very quickly generates potential itineraries with costs, total travel time (driving included), etc.

Post reply on HN