What's crazy is you've influenced them to spend real effort ensuring their model is good at generating animated svgs of animals operating vehicles.

The most absurd benchmaxxing.

https://x.com/jeffdean/status/2024525132266688757?s=46&t=ZjF...

It's an excellent demonstration of the main issue I have with the Gemini family of models, they always go "above and beyond" to do a lot of stuff, even if I explicitly prompt against it. In this case, most of the SVG ends up consisting not just of a bike and a pelican, but clouds, a sun, a hat on the pelican and so much more.

Exactly the same thing happens when you code, it's almost impossible to get Gemini to not do "helpful" drive-by-refactors, and it keeps adding code comments no matter what I say. Very frustrating experience overall.

Does anyone understand why LLMs have gotten so good at this? Their ability to generate accurate SVG shapes seems to greatly outshine what I would expect, given their mediocre spatial understanding in other contexts.

Models are soon going to start benchmaxxing generating SVGs of pelicans on bikes

It seems they trained the model to output good svg’s.

In their blog post[1], first use case they mention is svg generation. Thus, it might not be any indicator at all anymore.

[1] https://blog.google/innovation-and-ai/models-and-research/ge...

Did you stop using the more detailed prompt? I think you described it here: https://simonwillison.net/2025/Nov/18/gemini-3/

Less pretty and more practical, it's really good at outputting circuit designs as SVG schematics.

https://www.svgviewer.dev/s/dEdbH8Sw

Ugh, the gears and chain don't mesh and there's no sprocket on the rear hub

But seriously, I can't believe LLMs are able to one-shot a pelican on a bicycle this well. I wouldn't have guessed this was going to emerge as a capability from LLMs 6 years ago. I see why it does now, but... It still amazes me that they're so good at some things.

What do you think this particular prompt is evaluating for?

The more popular these particular evals are, the more likely the model will be trained for them.

At this point, the pelican benchmark became so widely used that there must be high quality pelicans in the dataset, I presume. What about generating an okapi on a bicycle instead?

What is that, a snack in the basket?

Wonder when will we get something other than a side view

Great pelican but what’s up with that fish in the basket?

How about STL files for 3d printing pelicans!

is there something in your prompt about hats? why the pelican always wearing a hat recently?!

Not even animated? This is 2026.

I used the AI studio link and tried running it with the temperature set to 1.75: https://jsbin.com/locodaqovu/edit?html,output

I hope we keep beating this dead horse some more, I'm still not tired of it.

I had an interesting experience recently where I ran Opus 4.6 against a problem that o4-mini had previously convinced me wasn't tractable... and Opus 4.6 found me a great solution. https://github.com/simonw/sqlite-chronicle/issues/20

This inspired me to point the latest models at a bunch of my older projects, resulting in a flurry of fixes and unblocks.

Yeah I keep maintaining a specific app I built with gpt 5.1 codex max with that exact model because it continues to work for the requests I send it, and attempts with other models even 5.2 or 5.3 codex seemed to have odd results. If I were superstitious I would say it’s almost like the model that wrote the code likes to work on the code better. Perhaps there’s something about the structure it created though that it finds easier to understand…

> It feels like we are now able to manage incredibly smart engineers for a month at the price of a good sushi dinner.

In my experience it’s more like idiot savant engineers. Still remarkable.

I have long suspected that a large part of people's distaste for given models comes from their comfort with their daily driver.

Which I guess feeds back to prompting still being critical for getting the most out of a model (outside of subjective stylistic traits the models have in their outputs).

Sushy dinner? What are you building with AI, a calculator?

Gemini just doesn’t do even mildly well in agentic stuff and I don’t know why.

OpenAI has mostly caught up with Claude in agentic stuff, but Google needs to be there and be there quickly

Glad I’m not the only one who experienced this. I have a paid antigravity subscription and most of the time I use Claude models due to the exact issues you have pointed out.

Don't get me started on the thinking tokens. Since 2.5P the thinking has been insane. "I'm diving in to the problem", "I'm fully immersed" or "I'm meticulously crafting the answer"

Is the thinking token stream obfuscated?

Im fully immersed

Hmm, interesting..

My workflow is to basically use it to explain new concepts, generate code snippets inline or fill out function bodies, etc. Not really generating code autonomously in a loop. Do you think it would excel at this?

yeah, g3p is as smart or smarter as the other flagships but it's just not reliable enough, it will go into "thinking loops" and burn 10s of 1000s of tokens repeating itself.

https://blog.brokk.ai/gemini-3-pro-preview-not-quite-baked/

hopefully 3.1 is better.

If we don't see a huge gain on the long-term horizon thinking reflected with the Vendor-Bench 2, I'm not going to switch away from CC. Until Google can beat Anthropic on that front, Claude Code paired with the top long-horizon models will continue to pull away with full stack optimizations at every layer.

still no minimal reasoning in G3.1P :(

(this is why Opus 4.6 is worth the price -- turning off thinking makes it 3x-5x faster but it loses only a small amount of intelligence. nobody else has figured that out yet)

Sounds like the update is mostly system prompt + changes to orchestration / tool use around the core model, if the knowledge cutoff is unchanged

Some people are suggesting that this might actually be in the training set. Since I can't rule that out, I tried a different version of the question, with an elephant instead of a car:

> It's a hot and dusty day in Arizona and I need to wash my elephant. There's a creek 300 feet away. Should I ride my elephant there or should I just walk there by myself?

Gemini said:

That sounds like quite the dusty predicament! Given the options, you should absolutely ride (or lead) your elephant to the creek.

Here is the straightforward reality of the situation:

    The Logistical Nightmare of Walking Alone: If you walk to the creek by yourself, your elephant stays at your starting point. Elephants require a massive amount of water for a bath. Unless you are planning an extreme workout carrying hundreds of buckets of water 300 feet back through the Arizona heat, you're going to have a very bad time—and the elephant will stay dusty.

    The Perks of Going Together: 300 feet is a very short, easy stroll for an elephant. Plus, elephants generally love water and mud! Letting your elephant get right into the creek will make the washing process much easier for you and much more enjoyable for them. They can even use their trunk to help hose themselves down.

Would you like some tips on the best methods and tools for scrubbing down an elephant?

GPT-OSS-120b, a (downloadable) model released more than half a year ago also gets that right, I'm not sure this is such a great success.

> Would you like me to check the local weather forecast to make sure it's not going to rain right after you wash it?

Regardless of what I do, the days I decide to wash my car, it ALWAYS rains the day after, even if I look at the weather report and it says sunny. Cute that Gemini thinks it can predict it better than universe's will.

The question of course is, did it get the car wash question right because it is "the car wash question" or because it could actually infer why the car needed to be there?

I think we need to reevaluate what purpose these sorts of questions serve and why they're important in regards to judging intelligence.

The model getting it correct or not at any given instance isn't the point, the point is if the model ever gets it wrong we can still assume that it still has some semblance of stochasticity in its output, given that a model is essentially static once it is released.

Additionally, hey don't learn post training (except for in context which I think counts as learning to some degree albeit transient), if hypothetically it answers incorrectly 1 in 50 attempts, and I explain in that 1 failed attempt why it is wrong, it will still be a 1-50 chance it gets it wrong in a new instance.

This differs from humans, say for example I give an average person the "what do you put in a toaster" trick and they fall for it, I can be pretty confident that if I try that trick again 10 years later they will probably not fall for it, you can't really say that for a given model.

The answer here is why I dislike Gemini, though it gets the correct answer, it's far too verbose.

Truly we entering the era of AGI.

They probably had time to toss that example in the training soup.

I agree completely. I don't know how anyone can be building on these models when all of them are either deprecated or not actually released yet. As someone who has production systems running on the deprecated models, this situation really causes me grief.

You are reading your link wrong. They are deprecating 2.5-preview models. 2.5 (including lite) are up till at least sept/oct 26.

I haven't seen any deprecation notices for 2.5 yet, just for 2. I'd expect (and hope) the deprecation timeline for 2.5 is longer since 3.0 is still in preview. Maybe they just default to 1 year here?

> Note: The shutdown dates listed in the table indicate the /earliest/ possible dates on which a model might be retired. We will communicate the exact shutdown date to users with advance notice to ensure a smooth transition to a replacement model.

This feels very Google

Interesting how it went a bit more 3D with the style of that one compared to the pelican I got.

can we move on from SVG to 3D models at some point?

I'm thinking now that as models get better and better at generating SVGs, there could be a point where we can use them to just make arbitrary UIs and interactive media with raw SVGs in realtime (like flash games).

On the other hand, creation of other vector image formats (eg. "create a postscript file showing a walrus brushing its teeth") hasn't improved nearly so much.

Perhaps they're deliberately optimising for SVG generation.

Good to see it wearing a helmet. Their safety team must be on their game.

your question may have become part of the training data with how much coverage there was around it. perhaps you should devise a new test :P

100% agreed. I wish someone would make a test for how reliably the LLMs follow tool use instructions etc. The pelicans are nice but not useful for me to judge how well a model will slot into a production stack.

I've been using it lately with OpenCode and it's working pretty well (except for API reliability issues).

> For those building with a mix of bash and custom tools, Gemini 3.1 Pro Preview comes with a separate endpoint available via the API called gemini-3.1-pro-preview-customtools. This endpoint is better at prioritizing your custom tools (for example view_file or search_code).

It sounds like there was at least a deliberate attempt to improve it.

You can delete the billing from a given API key

May be very silly of me, but I avoid using Gemini on my personal Google account. I use it at work, because my employer provides it.

I am scared some automated system may just decide I am doing something bad and terminate my account. I have been moving important things to Proton, but there are some stuff that I couldn't change that would cause me a lot of annoyance. It's not trivial to set up an alternative account just for Gemini, because my Google account is basically on every device I use.

I mostly use LLMs as coding assistant, learning assistant, and general queries (e.g.: It helped me set up a server for self hosting), so nothing weird.

So much this.

It's absolutely amazing how hostile Google is to releasing billing options that are reasonable, controllable, or even fucking understandable.

I want to do relatively simple things like:

1. Buy shit from you

2. For a controllable amount (ex - let me pick a limit on costs)

3. Without spending literally HOURS trying to understand 17 different fucking products, all overlapping, with myriad project configs, api keys that should work, then don't actually work, even though the billing links to the same damn api key page, and says it should work.

And frankly - you can't do any of it. No controls (at best delayed alerts). No clear access. No real product differentiation pages. No guides or onboarding pages to simplify the matter. No support. SHIT LOADS of completely incorrect and outdated docs, that link to dead pages, or say incorrect things.

So I won't buy shit from them. Period.

You could always use it through Copilot. The credits based billing is pretty simple without surprise charges.

use openrouter instead

When I worked there, there was a mix of training on nvidia GPUs (especially for sparse problems when TPUs weren't as capable), CPUs, and TPUs. I've been gone for a few years but I've heard a few anecdotal statements that some of their researchers have to use nvidia GPUs because the TPUs are busy.

no. only tpus

Another reason to use Gemini then.

Less impact on gamers…

Bla bla bla yada sustainability yada often come with large better growing faster...

It's such an uninformative piece of marketing crap

You can really notice the tool use problems. They gotta get on that. The agent trend seems real, and powerful. They can't afford to fall behind on it.

yeah, it seems to me like Gemini is a little behind on the current RL patterns and also they dont seem interested in really creating a dedicated coding model. I think they have so much product surface (search, AI mode, gmail, youtube, chrome etc), they are prioritizing making the model very general. but who knows im just talking out of my ass.

These improvements are one of the things specifically called out on the submitted page

In other words: they just need to motivate their employees while giving in to finance's demands to fire a few thousand every month or so ...

And don't forget, it's not just direct motivation. You can make yourself indispensable by sabotaging or at least not contributing to your colleagues' efforts. Not helping anyone, by the way, is exactly what your managers want you to do. They will decide what happens, thank you very much, and doing anything outside of your org ... well there's a name for that, isn't there? Betrayal, or perhaps death penalty.

To really confuse it, ask it to take that tricycle with the platypus on it to a car wash.

For a moment I assumed the output would look like Perry the Platipus from the Disney (I think?) show. It's suprising to me (as a layman) that a show with lots of media that would've made it to the training corpus didn't show up.

that's better than i thought it would be

Now I need to write more tests.

It's a bit hard to trick reasoning models, because they explore a lot of the angles of a problem, and they might accidentally have an "a-ha" moment that leads them on the right path. It's a bit like doing random sampling and stumbling upon the right result after doing gradient descent from those points.

Gemini sounds less personal, but I think that is good. From my experience, the quality of response is much higher than ChatGPT or Grok, and it cites real sources. I want to have a mini-wikipedia response for my questions, not a friend's group chat response

I have the opposite viewpoint:

If a model doesn't optimize the formatting of its output display for readability, I don't want to read it.

Tables, embedded images, use of bulleted lists and bold/italicizing etc.

It definitely has the worst "voice" in my opinion. Feels very overachieving McKinsey intern to me.

I'm not familiar with Openclaw and but the trick to solve this would be to embed a style reminder at the bottom of each user message and ideally hide that from the user with the UI.

This is how roleplay apps like Sillytavern customize the experience for power users by allowing hidden style reminders as part of the user message that accompany each chat message.

I think they all output that bold lettering, point by point style output. I strongly suspect it's part of a synthetic data pipeline all these AI companies have, and it improves performance. Claude seems to be the least of them, but it will start writing code at the drop of a hat. What annoys me in Gemini is that it has a really strange tendency to come up with weird analogies, especially in Pro mode. You'll be asking it about something like red black trees and it'll say "Red Black Trees (The F1 of Tree Data Structures)".

You just articulated why I struggle to personally connect with Gemini. It feels so unrelatable and exhausting to read its output. I prefer to read Opus/Deepseek/GLM over Gemini, Qwen and the open source GPT models. Maybe it is RLHF that is creating my distaste from using it. (I pay for Gemini; I should be using it more... but the outputs just bug me and feel more work to get actionable insight.)

I have no issues adjusting gemini tone & style with system prompt content

> I speculated that 3 pro was 3.1

?

When 3 came out they mentioned that flash included many improvements that didn't make it into pro (via an hn comment). I imagine this release includes those.

Gemini 3 Pro (high) is a joke compared to Gemini 3 Flash in Antigravity, except it's not even funny. Flash is insane value, and super capable, too. I've had it implement a decompiler for very obscure bytecode, and it was passing all tests in no time. PITA to refactor later, but not insurmountable. Gemini 3 Pro (high) choked on this problem in the early stages... I'm looking forward to comparing 3.1 Pro vs 3.0 Flash, hopefully they have improved on it enough to finally switch over.

It reads videos at 1fps by default. You have to set the video resolution to high in ai studio

I don't understand this sentiment. It may hold true for other LLM use cases (image generation, creative writing, summarizing large texts), but when it comes to coding specifically, Google is *always* behind OpenAI and Anthropic, despite having virtually infinite processing power, money, and being the ones who started this race in the first place.

Until now, I've only ever used Gemini for coding tests. As long as I have access to GPT models or Sonnet/Opus, I never want to use Gemini. Hell, I even prefer Kimi 2.5 over it. I tried it again last week (Gemini Pro 3.0) and, right at the start of the conversation, it made the same mistake it's been making for years: it said "let me just run this command," and then did nothing.

My sentiment is actually the opposite of yours: how is Google *not* winning this race?

I hope they fail.

I honestly do not wish Google to have the best model out there and be forced to use their incomprehensible subscription / billing / project management whatever shit ever again.

I don’t know what their stuff cost. I don’t know why would I use vertex or ai studio. What is included in my subscription what is billed per use.

I pray that whatever they build fails and burns.

More like half of Google's AI team is hanging out on HN, and they can optimise for that outcome to get a good rep among the dev community.

The hallucination rate with the Gemini family has always been my problem with them. Over the last year they’ve made a lot of progress catching the Gemini models up to/near the frontier in general capability and intelligence, but they still felt very late 2024 in terms of hallucination rate.

Which made the Gemini models untrustworthy for anything remotely serious, at least in my eyes. If they’ve fixed this or at least significantly improved, that would be a big deal.

But actual progress seems to be slower. These modes are releasing more often but aren’t big leaps.

Deep Think is a few 3.1 models working together. It was suspected last week that Deep Think was composed using the new 3.1 model.

3.1 == model

deep think == turning up thinking knob (I think)

deep research == agent w/ search

Bad news, John Google told me they already quantized it immediately after the benchmarks were done and it sucks now.

I miss when Gemini 3.1 was good. :(

I think there is a pattern it will always be nerfed the few weeks before launching a new model. Probably because they are throwing a bunch of compute at the new model.

What are you talking about?

I use it as my main platform right now both for work/swe stuff, and person stuff. It works pretty well, they have the full suite of tools I want from general LLM chat, to notebookLM, to antigravity.

My main use-cases outside of SWE generally involve the ability to compare detailed product specs and come up with answers/comparisons/etc... Gemini does really well for that, probably because of the deeper google search index integration.

Also I got a year of pro for free with my phone....so thats a big part.

I use it in Google Search. For example yesterday I typed in Google "postgres generate series 24 hour" and this morning "ffmpeg convert mp4 to wav". Previously I would have clicked on the first StackOverflow result (RIP), now I just take it from the Gemini summary (I'd say 95% of the time it's correct for basic programming language questions. I remember some hallucinations about psycopg3 and date-fns tho. As usual with AI, you need to already know the answer, at least partially, to detect the bs).

Also what's great about Gemini in Google Search is that the answer comes with several links, I use them sometimes to validate the correctness of the solution, or check how old the solution is (I've never used chatGPT so I don't know if chatGPT does it).

I use the Gemini web interface just as I would ChatGPT. They also have coding environment analogues of Claude-Code in Anti-gravity and Gemini-CLI.

When you sign up for the pro tier you also get 2TB of storage, Gemini for workspace and Nest Camera history.

If you're in the Google sphere it offers good value for money.

I feel like Gemini 3 was incredible on non-software/coding research. I have learned so much systems biology the last two months it blows my mind.

I had only started using Opus 4.6 this week. Sonnet it seems like is much better at having a long conversation with. Gemini is good for knowledge retrieval but I think Opus 4.6 has caught up. The biggest thing that made Gemini worth it for me the last 3 months is I crushed it with questions. I wouldn't have even got 10% of the Opus use that I got from Gemini before being made to slow down.

I have a deep research going right now on 3.1 for the first time and I honestly have no idea how I am going to tell if it is better than 3.

It seems like agentic coding Gemini wasn't as good but just asking it to write a function, I think it only didn't one shot what I asked it twice. Then fixed the problem on the next prompt.

I haven't logged in to bother with chatGPT in about 3 months now.

Gemini has an obvious edge over its competitors in one specific area: Google Search. The other LLMs do have a Web Search tool but none of them are as effective.

I personally use it as my general purpose and coding model. It's good enough for my coding tasks most of the time, has very good and rapid web search grounding that makes the Google index almost feel like part of its training set, and Google has a family sharing plan with individual quotas for Google AI Pro at $20/month for 5 users which also includes 2 TB in the cloud. Family sharing is a unique feature for Gemini 3 Flash Thinking (300 prompts per day and user) & Pro (100 prompts per day and user).

I find gemini to be the best at travel planning and for story telling of geographical places. For a road trip, I tried all three mainstream providers and I liked Gemini (also personal preference because Gemini took a verbose approach instead of bullet points from others) for it's responses, ways it discovered stories about places I wanted to explore, places it suggested for me and things it gave me to consider those places in the route.

I have swapped to using gemini over chatgpt for casual conversation and question answering. there are some lacking features in the app but i get faster and more intelligent responses.

I am a professional software developer who has been programming for 40 years (C, C++, Python, assembly, any number of other languages). I work in ML (infrastructure, not research) and spent a decade working at Google.

In short, I consider Gemini to be a highly capable intern (grad student level) who is smarter and more tenacious than me, but also needs significant guidance to reach a useful goal.

I used Gemini to completely replace the software stack I wrote for my self-built microscope. That includes:

writing a brand new ESP32 console application for controlling all the pins of my ESP32 that drives the LED illuminator. It wrote the entire ESP-IDF project and did not make any major errors. I had to guide with updated prompts a few times but otherwise it wrote the entire project from scratch and ran all the build commands, fixing errors along the way. It also easily made a Python shared library so I can just import this object in my Python code. It saved me ~2-3 days of working through all the ESP-IDF details, and did a better job than I would have.

writing a brand new C++-based Qt camera interface (I have a camera with a special SDK that allows controlling strobe and trigger and other details. It can do 500FPS). It handled all the concurrency and message passing details. I just gave it the SDK PDF documentation for the camera (in mixed english/chinese), and asked it to generate an entire project. I had to spend some time guiding it around making shared libraries but otherwise it wrote the entire project from scratch and I was able to use it to make a GUI to control the camera settings with no additional effort. It ran all the build commands and fixed errors along the way. Saved me another 2-3 days and did a better job than I could have.

Finally, I had it rewrite the entire microscope stack (python with qt) using the two drivers I described above- along with complex functionality like compositing multiple images during scanning, video recording during scanning, mesaurement tools, computer vision support, and a number of other features. This involved a lot more testing on my part, and updating prompts to guide it towards my intended destination (fully functional replacement of my original self-written prototype). When I inspect the code, it definitely did a good job on some parts, while it came up with non-ideal solutions for some problems (for example, it does polling when it could use event-driven callbacks). This saved literally weeks worth of work that would have been a very tedious slog.

From my perspective, it's worked extremely well: doing what I wanted in less time than it would take me (I am a bit of a slow programmer, and I'm doing this in hobby time) and doing a better job (With appropriate guidance) than I could have (even if I'd had a lot of time to work on it). This greatly enhances my enjoyment of my hobby by doing tedious work, allowing me to spend more time on the interesting problems (tracking tardigrades across a petri dish for hours at a time). I used gemini pro 3 for this- it seems to do better than 2.5, and flash seemed to get stuck and loop more quickly.

I have only lightly used other tools, such as ChatGPT/Codex and have never used Claude. I tend to stick to the Google ecosystem for several reasons- but mainly, I think they will end up exceeding the capabilities of their competitors, due to their inherent engineering talent and huge computational resources. But they clearly need to catch up in a lot of areas- for example, the VS Code Gemini extension has serious problems (frequent API call errors, messed up formatting of code/text, infinite loops, etc).

Various friends of mine work in non-technology companies (banking, industries, legal, Italy) and in pretty much all of them there's Gemini enterprise + NotebookLM.

In all of them the approach is: this is the solution, now find problems you can apply it to.

I use Gemini for personal stuff such as travel planning and research on how to fix something, which product to buy, etc. My company has as Pro subscription so I use that instead of ChatGPT.

I'd use it for planning, knowledge, and anything visual.

I use gemini for everything because I trust google to keep the data I send them safe, because they know how to run prod at scale, and they are more environmentally friendly than everyone else (tpu,us-central1).

This includes my custom agent / copilot / cowork (which uses vertex ai and all models therein). This is where I do more searching now (with genAi grounding) I'm about to work on several micro projects that will hold Ai a little differently.

All that being said, google Ai products suck hard. I hate using every one of them. This is more a reflection on the continued degradation of PM/Design at Big G, from before Ai, but accellationally worse since. I support removing Logan from the head of this shit show

disclaimer: long time g-stan, not so stan any more

Gemini-3.0-flash-preview came out right away with the 3.0 release and I was expecting 3.0-flash-lite before a bump on the pro model. I wonder if they have abandoned that part of the Pareto/price-performance.

Lol, and this line:

> Geminin 3.1 Pro can comprehend vast datasets

Someone was in a hurry to get this out the door.

but is it still terrible at tool calls in actual agentic flows?

I don't think models blow other models anymore. We have the big 3 which are neck to neck in most benchmarks and the rest. I doubt that 5.3 will blow the others.

Benchmarks aren't everything.

Gemini consistently has the best benchmarks but the worst actual real-world results.

Every time they announce the best benchmarks I try again at using their tools and products and each time I immediately go back to Claude and Codex models because Google is just so terrible at building actual products.

They are good at research and benchmaxxing, but the day to day usage of the products and tools is horrible.

Try using Google Antigravity and you will not make it an hour before switching back to Codex or Claude Code, it's so incredibly shitty.

I agree, according to Googles terms you are not allowed to use the preview model for production use cases. And 3.0 has been in preview for a loooong time now :(

I don't see it even after refresh. Are you using the opencode-gemini-auth plugin as well?

It is super interesting that this is the same thing that happened in November (ie all labs shipping around the same week 11/12-11/23).

https://github.com/google-gemini/gemini-cli

My sense is that the Gemini models are very capable but the Gemini CLI experience is subpar compared to Claude Code and Codex. I'm guess that it's the harness but since it can get confused, fall into doom loops, and generally lose the plot in a way that the model does not in Gemini Studio or the Gemini app.

I think a bunch of these harnesses are open source so it surprises me that there can be such a gulf between them.

How are you prompting it to draw diagrams in drawio