Posted by MallocVoidstar 7 hours ago
Card: https://deepmind.google/models/model-cards/gemini-3-1-pro/
I'm a former Googler and know some people near the team, so I mildly root for them to at least do well, but Gemini is consistently the most frustrating model I've used for development.
It's stunningly good at reasoning, design, and generating the raw code, but it just falls over a lot when actually trying to get things done, especially compared to Claude Opus.
Within VS Code Copilot Claude will have a good mix of thinking streams and responses to the user. Gemini will almost completely use thinking tokens, and then just do something but not tell you what it did. If you don't look at the thinking tokens you can't tell what happened, but the thinking token stream is crap. It's all "I'm now completely immersed in the problem...". Gemini also frequently gets twisted around, stuck in loops, and unable to make forward progress. It's bad at using tools and tries to edit files in weird ways instead of using the provided text editing tools. In Copilot it, won't stop and ask clarifying questions, though in Gemini CLI it will.
So I've tried to adopt a plan-in-Gemini, execute-in-Claude approach, but while I'm doing that I might as well just stay in Claude. The experience is just so much better.
For as much as I hear Google's pulling ahead, Anthropic seems to be to me, from a practical POV. I hope Googlers on Gemini are actually trying these things out in real projects, not just one-shotting a game and calling it a win.
I think it speaks to the broader notion of AGI as well.
Claude is definitively trained on the process of coding not just the code, that much is clear.
Codex has the same limitation but not quite as bad.
This may be a result of Anthropic using 'user cues' with respect to what are good completions and not, and feeding that into the tuning, among other things.
Anthropic is winning coding and related tasks because they're focused on that, Google is probably oriented towards a more general solution, and so, it's stuck in 'jack of all trades master of none' mode.
I have a pretty crude mental model for this stuff but Opus feels more like a guy to me, while Codex feels like a machine.
I think that's partly the personality and tone, but I think it goes deeper than that.
(Or maybe the language and tone shapes the behavior, because of how LLMs work? It sounds ridiculous but I told Claude to believe in itself and suddenly it was able to solve problems it wouldn't even attempt before...)
OpenAI has mostly caught up with Claude in agentic stuff, but Google needs to be there and be there quickly
Most of Gemini's users are Search converts doing extended-Search-like behaviors.
Agentic workflows are a VERY small percentage of all LLM usage at the moment. As that market becomes more important, Google will pour more resources into it.
I do wonder what percentage of revenue they are. I expect it's very outsized relative to usage (e.g. approximately nobody who is receiving them is paying for those summaries at the top of search results)
via Anthropic
https://www.anthropic.com/research/measuring-agent-autonomy
this doesn’t answer your question, but maybe Google is comfortable with driving traffic and dependency through their platform until they can do something like this
Nobody is paying for Search. According to Google's earnings reports - AI Overviews is increasing overall clicks on ads and overall search volume.
No ads, no forced AI overview, no profit centric reordering of results, plus being able to reorder results personally, and more.
For example the APEX-Agents benchmark for long time horizon investment banking, consulting and legal work:
1. Gemini 3.1 Pro - 33.2% 2. Opus 4.6 - 29.8% 3. GPT 5.2 Codex - 27.6% 4. Gemini Flash 3.0 - 24.0% 5. GPT 5.2 - 23.0% 6. Gemini 3.0 Pro - 18.0%
I'll withhold judgement until I've tried to use it.
Let's give it a couple of days since no one believes anything from benchmarks, especially from the Gemini team (or Meta).
If we see on HN that people are willing switching their coding environment, we'll know "hot damn they cooked" otherwise this is another wiff by Google.
I think this is classic precision/recall issue: the model needs to stay on task, but also infer what user might want but not explicitly stated. Gemini seems particularly bad that recall, where it goes out of bounds
Yes, gemini loops but I've found almost always it's just a matter of interrupting and telling it to continue.
Claude is very good until it tries something 2-3 times, can't figure it out and then tries to trick you by changing your tests instead of your code (if you explicitly tell it not to, maybe it will decide to ask) OR introduce hyper-fine-tuned IFs to fit your tests, EVEN if you tell it NOT to.
- it is "lazy": I keep having to tell it to finish, or continue, it wants to stop the task early.
- it hallucinates: I have arguments with it about making up API functions to well known libraries which just do not exist.
Makes you wonder though how much of the difference is the model itself vs Claude Code being a superior agent.
Claude provides nicer explanations, but when it comes to CoT tokens or just prompting the LLM to explain -- I'm very skeptical of the truthfulness of it.
Not because the LLM lies, but because humans do that also -- when asked how the figured something, they'll provide a reasonable sounding chain of thought, but it's not how they figured it out.
tldr; It is great at search, not so much action.
It's not very complex, but a great time saver
And yet it happily told me what I exactly wanted it to tell me - rewrite the goddamn thing using the (C++) expression templates. And voila, it took "it" 10 minutes to spit out the high-quality code that works.
My biggest gripe for now with Gemini is that Antigravity seems to be written by the model and I am experiencing more hiccups than I would like to, sometimes it's just stuck.
I have noticed that LLM's seem surprisingly good at translating from one (programming) language to another... I wonder if transforming a generic mathematical expression into an expression template is a similar sort of problem to them? No idea honestly.
As an ex-Googler part of me wonders if this has to do with the very ... bespoke ... nature of the developer tooling inside Google. Though it would be crazy for them to be training on that.
Im fully immersed
It's likely filled with "Aha!" and "But wait!" statements.
What does that mean? Are you able to read the raw cot? how?
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?
https://blog.brokk.ai/gemini-3-pro-preview-not-quite-baked/
hopefully 3.1 is better.
Maybe it is just a genius business strategy.
I wonder if there is some form of cheating. Many times I found that after a while Gemini becomes like a Markov chain spouting nonsense on repeat suddenly and doesn't react to user input anymore.
Think about ANY other product and what you'd expect from the competition thats half the price. Yet people here act like Gemini is dead weight
____
Update:
3.1 was 40% of the cost to run AA index vs Opus Thinking AND SONNET, beat Opus, and still 30% faster for output speed.
https://artificialanalysis.ai/?speed=intelligence-vs-speed&m...
So a lot of these things are relative.
Now if that equation plays out 20K times a day, well that's one thing, but if it's 'once a day' then the cost basis becomes irrelevant. Like the cost of staplers for the Medical Device company.
Obviously it will matter, but for development ... it's probably worth it to pay $300/mo for the best model, when the second best is $0.
For consumer AI, the math will be different ... and that will be a big deal in the long run.
But I agree: If they can get there (at one point in the past year I felt they were the best choice for agentic coding), their pricing is very interesting. I am optimistic that it would not require them to go up to Opus pricing.
But man, people are really avid about it being an awful model.
Google undercutting/subsidizing it's own prices to bite into Anthropic's market share (whilst selling at a loss) doesn't automatically mean Google is effective.
But Flash is 1/8 the cost of sonnet and its not impressive?
Counterpoint: price will matter before we hit AGI
Gemini definitely has its merits but for me it just doesn't do what other models can. I vibe-coded an app which recommends me restaurants. The app uses gemini API to make restaurants given bunch of data and prompt.
App itself is vibe-coded with Opus. Gemini didn't cut it.
Opus is absurdly good in Claude code but theres a lot of use cases Gemini is great at.
I think Google is further behind with the harness than the model
Is it? Honestly, I still chuckle about black Nazis and the female Indian Popes. That was my first impression of Gemini, and first impressions are hard to break. I used Gemini’s VL (vision) for something and it refused to describe because it assumed it was NSFW imagery, which is was not.
I also question statis as an obvious follow up. Is Gemini equal to Opus? Today? Tomorrow? Has Google led the industry thus far and do I expect them to continue?
Counterpoint to that would be that with natural language input and output, that LLM specific tooling is rare and it is easy to switch around if you commoditize the product backend.
In contrast, the vs code plugin was pretty bad, and did crazy things like mix languages
So far I like how it’s less verbose than its predecessor. Seems to get to the point quicker too.
While it gives me hope, I am going to play it by the ear. Otherwise it’s going to be - Gemini for world knowledge/general intelligence/R&D and Opus/Sonnet 4.6 to finish it off.
It's totally possible to build entire software products in the fraction of the time it took before.
But, reading the comments here, the behaviors from one version to another point version (not major version mind you) seem very divergent.
It feels like we are now able to manage incredibly smart engineers for a month at the price of a good sushi dinner.
But it also feels like you have to be diligent about adopting new models (even same family and just point version updates) because they operate totally differently regardless of your prompt and agent files.
Imagine managing a team of software developers where every month it was an entirely new team with radically different personalities, career experiences and guiding principles. It would be chaos.
I suspect that older models will be deprecated quickly and unexpectedly, or, worse yet, will be swapped out with subtle different behavioral characteristics without notice. It'll be quicksand.
They come up with passable solutions and are good for getting juices flowing and giving you a start on a codebase, but they are far from building "entire software products" unless you really don't care about quality and attention to detail.
This inspired me to point the latest models at a bunch of my older projects, resulting in a flurry of fixes and unblocks.
More realistically, I could see particular languages and frameworks proving out to be more well-designed and apt for AI code creation; for instance, I was always too lazy to use a strongly-typed language, preferring Ruby for the joy of writing in it (obsessing about types is for a particular kind of nerd that I've never wanted to be). But now with AI, everything's better with strong types in the loop, since reasoning about everything is arguably easier and the compiler provides stronger guarantees about what's happening. Similarly, we could see other linguistic constructs come to the forefront because of what they allow when the cost of implementation drops to zero.
I think the main limitation on the current models is not that cpu instructions aren't cpu instructions (even though they can be with .asm), it's that they are causal, the cpu would need to generate a binary entirely from start to finish sequentially.
If we learned something over the last 50 years of programming is that that's hard and that's why we invented programming languages? Why would it be simpler to just generate the machine code, sure maybe an LLM to application can exist, but my money is in that there will be a whole toolchain in the middle, and it will probably be the same old toolchain that we are using currently, an OS, probably Linux.
Isn't it more common that stuff builds on the existing infra instead of a super duper revolution that doesn't use the previous tech stack? It's much easier to add onto rather than start from scratch.
> Use triggers to track when rows in a SQLite table were updated or deleted
Just a note in case its interesting to anyone, sqlite compatible Turso database has CDC, a changes table! https://turso.tech/blog/introducing-change-data-capture-in-t...
In my experience it’s more like idiot savant engineers. Still remarkable.
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).
Careful.
Gemini simply, as of 3.0, isn't in the same class for work.
We'll see in a week or two if it really is any good.
Bravo to those who are willing to give up their time to test for Google to see if the model is really there.
(history says it won't be. Ant and OAI really are the only two in this race ATM).
Knowledge cutoff is unchanged at Jan 2025. Gemini 3.1 Pro supports "medium" thinking where Gemini 3 did not: https://ai.google.dev/gemini-api/docs/gemini-3
Compare to Opus 4.6's $5/M input, $25/M output. If Gemini 3.1 Pro does indeed have similar performance, the price difference is notable.
OpenAI: no big deal — sign up, pick your number of seats, and you’re all set.
Anthropic: also no big deal but there’s an obnoxious minimum purchase.
Google: first you have to try to figure out what the product is called. Then you need to figure out how to set the correct IAM rules. Then you have to sign up and pay for it. Maybe you succeed. Maybe you give up after an hour or two of cursing. Gemini is, of course, completely unable to help. (OpenAI clearly has not trained their models on how to operate their tools. Google’s models hallucinate Google’s product offerings so outrageously that I’m not sure I could tell. I haven’t asked Claude about Claude Code.)
At least the monthly pricing is similar once you get over the hurdles.
(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)
Isn't that a bit old?
Are Google planning to put any of their models into production any time soon?
Also somewhat funny that some models are deprecated without a suggested alternative(gemini-2.5-flash-lite). Do they suggest people switch to Claude?
When you build on something that can be rugpulled at any moment, that's really kind of on you.
(Another commenter pointed out that this is the earliest shutdown date and it won't necessarily be shut down on that date).
Where are you getting sept/Oct from? I see gemini-2.5-flash-image in October, but everything else looks like June/July to me?
But like everyone else I'm used to Google failing to care about products.
This held for internal APIs, facilities, systems more even than it did for the outside world. Which is terrible.
> 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 article[0] talks about 2 being deprecated.
It's still frustrating that they don't have proper production endpoints for 3.0 yet.
You are definitely going to have to drive it there—unless you want to put it in neutral and push!
While 200 feet is a very short and easy walk, if you walk over there without your car, you won't have anything to wash once you arrive. The car needs to make the trip with you so it can get the soap and water.
Since it's basically right next door, it'll be the shortest drive of your life. Start it up, roll on over, and get it sparkling clean.
Would you like me to check the local weather forecast to make sure it's not going to rain right after you wash it?
> 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?
You should definitely ride the elephant (or at least lead it there)!
Here is the logic:
If you walk there by yourself, you will arrive at the creek, but the dirty elephant will still be 300 feet back where you started. You can't wash the elephant if it isn't with you!
Plus, it is much easier to take the elephant to the water than it is to carry enough buckets of water 300 feet back to the elephant.
Would you like another riddle, or perhaps some actual tips on how to keep cool in the Arizona heat?
> 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.
Undeniable universal truth. I sometimes find myself making plans based on the fact that the most annoying possible outcome is also the most likely one.
This kind of reflexive criticism isn't helpful, it's closer to a fully generalized counter-argument against LLM progress, whereas it's obvious to anyone that models today can do things they couldn't do six months ago, let alone 2 years back.
I double checked and tested on AI Studio, since you can still access the previous model there:
>You should drive. >If you walk there, your car will stay behind, and you won't be able to wash it.
Thinking models consistently get it correct and did when the test was brand new (like a week or two ago). It is the opposite of surprising that a new thinking model continues getting it correct, unless the competitors had a time machine.
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.
I think that's why benchmarking is so hard for me to fully get behind, even if we do it over say, 20 attempts and average it. For a given model, those 20 attempts could have had 5 incredible outcomes and 15 mediocre ones, whereas another model could have 20 consistently decent attempts and the average score would be generally the same.
We at least see variance in public benchmarks, but in the internal examples that's almost never the case.
"create a svg of a unicorn playing xbox"
https://www.svgviewer.dev/s/NeKACuHj
Still some tweaks to the final result, but I am guessing with the ARC-AGI benchmark jumping so much, the model's visual abilities are allowing it to do this well.
I don't know if it got these abilities through generalization or if google gave it a dedicated animated SVG RL suite that got it to improve so much between models.
Regardless we need a new vibe check benchmark ala bicycle pelican.
So render ui elements using xml-like code in a web browser? You’re not going to believe me when I tell you this…
Which is the "left brain" approach vs the "right brain" approach of coming at dynamic videogames from the diffusion model direction which the Gemini Genie thing seems to be about.
Perhaps they're deliberately optimising for SVG generation.
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.
Just asking "Explain what this service does?" turns into
[No response for three minutes...]
+729 -522
"NEVER REMOVE LOGGING OR DEBUGGING INFO. If unsure, bias towards introducing sensible logging."
Or just
"NEVER REMOVE LOGGING OR DEBUGGING INFO."
Because your coworkers definitely are, and we're stack ranked, so it's a race (literally) to the bottom. Just send it...
(All this actually seems to do is push the burden on to their coworkers as reviewers, for what it's worth)
Edit: obviously inside something so it doesn't have access to the rest of my system, but enough access to be useful.
People that don't put out slop, mostly.
What I don't have time to do is debug obvious slop.
Built-in approval thing sounds like a good idea, but in practice it's unusable. Typical session for me was like:
About to run "sed -n '1,100p' example.cpp", approve?
About to run "sed -n '100,200p' example.cpp", approve?
About to run "sed -n '200,300p' example.cpp", approve?
Every one of these models is so great at propelling the ship forward, that I increasingly care more and more about which models are the easiest to steer in the direction I actually want to go.
Codex is very steerable to a fault, and will gladly "monkey paw" your requests to a fault.
Claude Opus will ignore your instructions and do what it thinks is "right" and just barrel forward.
Both are bad and papering over the actual issue which is these models don't really have the ability to actually selectively choose their behavior per issue (ie ask for followup where needed, ignore users where needed, follow instructions where needed). Behavior is largely global
Overall, I think it's probably better that it stay focused, and allow me to prompt it with "hey, go ahead and refactor these two functions" rather than the other way around. At the same time, really the ideal would be to have it proactively ask, or even pitch the refactor as a colleague would, like "based on what I see of this function, it would make most sense to XYZ, do you think that makes sense? <sure go ahead> <no just keep it a minimal change>"
Or perhaps even better, simply pursue both changes in parallel and present them as A/B options for the human reviewer to select between.
This has not been my experience. I do Elixir primarily and Gemini has helped build some really cool products and massive refactors along the way. And it would even pick up security issues and potential optimizations along the way
What HAS been an issue constantly though was randomly the model will absolutely not respond at all and some random error would occur which is embarrassing for a company like Google with the infrastructure they own.
Not like human programmers. I would never do this and have never struggled with it in the past, no...
That helped quite a bit but it would still go off on it's own from time to time.
You can make their responses fairly dry/brief.
There is a tradeoff though, as comments do consumer context. But I tend to pretty liberally dispense of instances and start with a fresh window.
Yeah, that sounds worse than "trying to helpful". Read the code instead, why add indirection in that way, just to be able to understand what other models understand without comments?
Be a proactive research partner: challenge flawed or unproven ideas with evidence; identify inefficiencies and suggest better alternatives with reasoning; question assumptions to deepen inquiry.The most absurd benchmaxxing.
https://x.com/jeffdean/status/2024525132266688757?s=46&t=ZjF...
I've been meaning to let coding agents take a stab at using the lottie library https://github.com/airbnb/lottie-web to supercharge the user experience without needing to make it a full time job
I'm not against pelicans!
If we picked something more common, like say, a hot dog with toppings, then the training contamination is much harder to control.
There's a specific term for this in education and applied linguistics: the washback effect.
- One thing to be aware of is that LLMs can be much smarter than their ability to articulate that intelligence in words. For example, GPT-3.5 Turbo was beastly at chess (1800 elo?) when prompted to complete PGN transcripts, but if you asked it questions in chat, its knowledge was abysmal. LLMs don't generalize as well as humans, and sometimes they can have the ability to do tasks without the ability to articulate things that feel essential to the tasks (like answering whether the bicycle is facing left or right).
- Secondly, what has made AI labs so bullish on future progress over the past few years is that they see how little work it takes to get their results. Often, if an LLM sucks at something that's because no one worked on it (not always, of course). If you directly train a skill, you can see giant leaps in ability with fairly small effort. Big leaps in SVG creation could be coming from relatively small targeted efforts, where none existed before.
Gemini was multimodal from the start, and is naturally better at doing tasks that involve pictures/videos/3d spatial logic/etc.
The newer chatgpt models are also now multimodal, which has probably helped with their svg art as well, but I think Gemini still has an edge here
Added more IF/THEN/ELSE conditions.
https://simonwillison.net/2025/Nov/13/training-for-pelicans-...
"Give me an illustration of a bicycle riding by a pelican"
"Give me an illustration of a bicycle riding over a pelican"
"Give me an illustration of a bicycle riding under a flying pelican"
So on and so forth. Or will it start to look like the Studio C sketch about Lobster Bisque: https://youtu.be/A2KCGQhVRTE
I wouldn't really even call it "cheating" since it has improved models' ability to generate artistic SVG imagery more broadly but the days of this being an effective way to evaluate a model's "interdisciplinary" visual reasoning abilities have long since passed, IMO.
It's become yet another example in the ever growing list of benchmaxxed targets whose original purpose was defeated by teaching to the test.
https://x.com/jeffdean/status/2024525132266688757?s=46&t=ZjF...
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...
Cost per task is still significantly lower than Opus. Even Opus 4.5
I did a larger circuit too that this is part of, but it's not really for sharing online.
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.
I have a feeling the most 'emergent' aspect was that LLMs have generally been able to produce coherent SVG for quite a while, likely without specific training at first. Since then I suspect there has been more tailored training because improvements have been so dramatic. Of course it makes sense that text-based images using very distinct structure and properties could be manipulated reasonably well by a text-based language model, but it's still fascinating to me just how well it can work.
Perhaps what's most incredible about it is how versatile human language is, even when it lacks so many dimensions as bits on a machine. Yet it's still cool that we can resurrect those bits at rest and transmogrify them back into coherent projections of photons from a screen.
I don't think LLMs are AGI or about to completely flip the world upside down or whatever, but it seems undeniably magical when you break it down.
You can try any combination of animal on vehicle to confirm that they likely didn't target pelicans directly though.
human adults are generally quite bad at drawing them, unless they spend a lot of time actually thinking about bicycles as objects
EDIT: And the chain should pass behind the seat stay.
how thoughtful of the ai to include a snack. truly a "thanks for all the fish"
The more popular these particular evals are, the more likely the model will be trained for them.
"make me a cartoon image of a pelican riding a bicycle, but make it from a front 3/4 view, that is riding toward the viewer."
The result was basically a head-on view, but I expect if you then put that back in and said, "take this image and vectorize it as an SVG" you'd have a much better time than trying to one-shot the SVG directly from a description.
... but of course, if that's so, then what's preventing the model from being smart enough to identify this workflow and follow it on its own to get the task completed?
It's a pretty funny and coherent touch!
Probably stuff it cannot fit in the gullet, or don't want there (think trash). I wouldn't expect a pelican to stash fish there, that's for sure.
It's obvious that pelican is riding long distance, no way a single fish is sufficiently energy dense for more than a few miles.
Can't the model do basic math???
Disclaimer: This is an unsubstantiated claim that i made up
I find this fascinating because it literally just happened in the past few months. Up until ~summer of 2025, the SVG these models made was consistently buggy and crude. By December of 2026, I was able to get results like this from Opus 4.5 (Henry James: the RPG, made almost entirely with SVG): https://the-ambassadors.vercel.app
And now it looks like Gemini 3.1 Pro has vaulted past it.
Yeah, since the invention of vector images, suddenly no one cares about raster images anymore.
Obviously not true, but that's how your comment reads right now. "Image" is very different from "Image", and one doesn't automagically replace the other.
We had high framerate (yes it was variable), bright, beautiful displays in the 1980s with the vectrex.
Hardest: the pelican must work