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

Gemini 3.7 Flash

blog.google

Post reply on HN
Print view View original

291–300 of 525 posts

Re: Gemini 3.7 Flash

#291

Post by onraglanroad »

Alifatisk wrote: post #202
mikepurvis wrote: post #187

Earlier quoted context omitted.

I'm curious how much people are manually curating context these days; I'm increasingly feeling for myself that it being auto-managed inside a front-end like claude code is not ideal, and I'd rather have more control over what exact files and pieces of discovery go into a particular prompt, and the ability to more easily "fork" a session and ask asides or make notes/todos in a way that doesn't disrupt or confuse a mor…

I am not sure this enlightens you with anything but I have a TODO.md file with three headlines. Todo, Doing and Done. The agent is aware of it and knows on which task we are on. On complete, it moves the user story from Doing to Done. I also have a MEMORY.md file that the agent read and writes in the beginning of a new conversation and at the end of our conversation to update stale information. These files are referr…

I like to call them TODO, TODOING. and TODONE. Keeps them in alphabetical order and is not in the slightest OCD...

Re: Gemini 3.7 Flash

#292

Post by asdfman123 »

simonw wrote: post #141

The "introductory pricing" for this 3.7 Flash model is really weird. It's scheduled to double in price on December 31, 2026, but who would anticipate still using this model five months from now? Especially since 3.6 Flash came out just three weeks ago! My first effort with default thinking level produced an ambitious pelican, let down by a flawed bicycle: https://tools.simonwillison.net/markdown-svg-renderer#url=ht..…

Maybe it's a way to kick people off the old models. "If you still want to keep using the old model you can, but you'd better pay a premium."

I work for Google and their free, internal Gemini API isn't quite as graceful. They once turned down a model arbitrarily and it broke our tests. I had to scramble to fix it, then build warning systems for the turndown as well as a special validator to make sure any upgrades make the same determinations.

Re: Gemini 3.7 Flash

#293

Post by swalsh »

simonw wrote: post #141

The "introductory pricing" for this 3.7 Flash model is really weird. It's scheduled to double in price on December 31, 2026, but who would anticipate still using this model five months from now? Especially since 3.6 Flash came out just three weeks ago! My first effort with default thinking level produced an ambitious pelican, let down by a flawed bicycle: https://tools.simonwillison.net/markdown-svg-renderer#url=ht..…

Yeah, so I'm going to confess. Ive built production AI systems that have very specific jobs, deployed them, and moved on. The cost is not noticeable, i had the system dialed in. Not worth the effort to reevaluate a newer model to see if its better in some way. Current model works, and I have other projects that are more important.

Re: Gemini 3.7 Flash

#294

Post by giarc »

jjcm wrote: post #106

Here's a image->html test. Gemini has always swung above its weight class for vision work, so I'm always eager to try it with this. Original images: https://image.non.io/neonRamenDesigns.webp Gemini 3.7 build: https://html.non.io/neonRamenGemini3.7 Opus 5 build for comparison: https://html.non.io/neonRamen Opus is still best in class for this, but it's worth noting how well Gemini 3.7 does vs a more comparable LLM pr…

Can you share what your prompt was for that?

Re: Gemini 3.7 Flash

#297

Post by knuppar »

ls_stats wrote: post #157

I don't get it, Google could heavily subsidy their Gemini models to make it more attractive, but they prefer to not do it. I don't know one soul who is using Gemini models to code. Even OpenAI who doesn't have money or capacity is offering their Luna model at $1.2 per 1M/out.

the race for the smartest/cheapest model is a race to the bottom. selling the tools is much more profitable.

Re: Gemini 3.7 Flash

#298

Post by WarmWash »

dudeinhawaii wrote: post #139

I want to like Gemini models but my problem thus far has been a lack of coding chops. They still make mistakes, importantly, without correcting them for things like hallucinated API calls or code that doesn't run but they never bothered building or running. I know a lot of this can be fixed with workflows but it still feels like a failing. GPT-5.6 or Claude models haven't delivered to me non-running code in ages. Whe…

It depends on if you are relying on all single shot tasks or are willing to iterate. Flash is quick and can make dumb mistakes, but it also can fix them quickly.

I've gotten good results with it, but it definitely is more hands on.

Re: Gemini 3.7 Flash

#299

Post by jaggederest »

piyh wrote: post #193
jjcm wrote: post #133

Earlier quoted context omitted.

Other thoughts: I really think Google has fallen behind here. Even as a high speed offering (this build took ~7min, which is pretty good!), it wont be able to claim dominance for long with cerebras announcing the Sol preview today: https://www.cerebras.ai/blog/accelerating-gpt-5-6-sol-ultraf... . It's not a bad model by any means, but I just don't know what situation I'd reach for 3.7 Flash first for. Google really n…

Sol on Cerebras is going to be expensive AF

Is it? I think waferscale might actually be cheaper per-token, it's just so many more tokens, and of course right now it's not a full buildout so the availability is limited as well. I'd imagine they'll be migrating to whichever inference method is least expensive, and I expect asics to be the ultimate answer.

Re: Gemini 3.7 Flash

#300

Post by krat0sprakhar »

Saline9515 wrote: post #230
krat0sprakhar wrote: post #215

Earlier quoted context omitted.

Can you help me understand how it is hard to get an API key from Google? You just head on over to http://aistudio.google.com/api-keys and create a key... not any different from platform.openai.com? Disclaimer: I work in Google so it might be that this link is not publicly well known

On top of being the hardest website to navigate, Google console a) doesn't have real time billing (!) b) doesn't allow you to set a budget limit. Sorry but it's not worth waking up with a 100k$ bill, fix your platform first.

Spend caps can now be set https://blog.google/innovation-and-ai/technology/developers-...
Post reply on HN