Comment by WarmWash
6 hours ago
Perhaps you haven't had the chance to use it, but 3.8 flash is the best model for talking too. Even routing Claudes output through 3.8 to have it explain whats going on is a breath of fresh air
6 hours ago
Perhaps you haven't had the chance to use it, but 3.8 flash is the best model for talking too. Even routing Claudes output through 3.8 to have it explain whats going on is a breath of fresh air
Agreed. It's very capable for something carrying the "flash" label, super fast, and very clear to read.
I'll have to try Gemini Flash for coding. The reason I haven't I used Gemini for coding is last time I tried it couldn't call tools very well.
I am a huge fan of Gemini Pro for chat... gemini somehow just knows the most obscure stuff. I'll double check something Gemini said and find the source is deep inside a hard to access scientific paper. Google just has the best index of the internet.
I remember the Gemini 2.5 Pro series was the best at text, but failed half of it's tool calls. They really redeemed themselves with the 3.5 Flash series, it's great. I love how fast it is. Now if only they could offer a subscription service for it...
Makes sense. When Google Jules was new, I experimented with it for a while and it was embarrassing how often it flubbed tool calls, often repeatedly. It tended to forget the working directory so almost every command needed two tries.
It's coding is still meh. Greenfield applets all day, but don't throw it in the jungle.
It's best for brain storming, rabbit holes, and image recognition.
Let the big models do the heavy lifting for now.
Agreed.
Even if you aren't coding, you really need to double check its answers. Flash 3.8 hallucinated a Keyence camera's max operating temperature for me, last week, and backed it up with "references".
It's still my favorite model for most non-coding stuff, though.
gemini 3.8 flash?
yes
I would if they let me bring the subscription I have to the harness of my choice.