you can run into payload too large errors, ingesting bunch of context, I use vercel's ai sdk so I can interchange between models but have 0 OpenAI and Claude credits or subscriptions. I use a combination of grepping files like a terminal tool and implemented a vector search database for fuzzy searches, Gemini chooses what tool it wants to use, I provide it create, read, update, delete, functions. There's a few tricks I do as well but if I tell you, you can probably prompt a clone . Sharing the full implementation is basically open sourcing the code.
The state of the art is moving so rapidly that, yeah, Copilot by Microsoft using gpt-5-mini:low is not going to be very good. And there are many places where AI has been implemented poorly, generally by people who have the distribution to force it upon many people. There are also plenty of people who use vibe coding tools and produce utterly atrocious codebases. That doesn't preclude the existence of effective AI tools, and people who are good at using them.
This is motivated pessimism. We knew in the 50s that breaking the speed of light was highly unlikely. We dreamed of the stars anyway. Now we refuse to dream, or to even attempt to solve the problems (a common pattern when discussing spaceflight is people who are blatantly searching for problems, rather than solutions), because we are pessimistic, devoid of imagination, and seek to legitimise our collective depression through scientific and engineering arguments.
You don't need to break the speed of light to get to the stars. Time dilation and space contraction mean that you can get there in as little time as you desire.
Everyone you knew on earth would be dead by the time you got back, but if it's just about you, the speed of light is no limitation at all. (The rocket equation, however, presents stupendous engineering challenges.)
Time dilation and space contraction only matter if you can reasonably achieve speeds of a significant portion of the speed of light. AFAIK nobody has even come up with a reasonable way to achieve this for lightweight probes, let alone for hundred-ton ships capable of carrying humans. And let's not forget the practical problems like all photons incoming from the front being blueshifted into ultrahard radiation that would make a point blank nuclear bomb seem like a small candle.
Realistically even getting to the nearest star in less than 400 years experienced time is way way WAY out of reach for now.
Laser accelerate a lightweight probe, probe lands on alien planet and self replicates a receiver and basic robot body. Send mind in the form of information at speed of light and download into robot body.
Something roughly along these lines was believable enough for the Altered Carbon universe.
Landing from relativistic speed would be a massive engineering problem, since you won't have a laser de-celerator on the other end. And landing on a planet would seem to require a rocket, which cannot be lightweight.
Not necessarily insoluble, but a massive unsolved problem.
Show us how to build machines, create factories, mines, chip fabs, etc., smelt steel, and so forth out of those bacteria and cells and you might have a point.
So what? Dilithium + antimatter + magic space warping was enough for the Star Trek universe. The sky is the limit for science fiction.
Just in that first paragraph:
- How do you stop at the other end? There won't be a large laser array at the receiving end and a laser probe will not have enough stored energy to decelerate itself.
- How exactly do you download a mind to be transmitted? We can't do it right now to be sure, and it's not clear we could ever accurately do that depending on how finely detailed a human brain is.
- How do you transmit it reliably over several hundred light years? Background radiation alone is enough to drown out any signal after a few dozen light years no matter how good your transmission is. Also, when do you start sending? You cannot possibly know which probes survived. (you DID send out at least a few hundred probes right? Don't forget to multiply laser energy requirements by the amount of probes)
- How does the receiving end download a mind into a robot body? We can't even begin to do that on Earth, not even with worms or flies. Humans are right out.
- How do we power the lasers? Conservative estimates have put required laser power at several gigawatts at least. Current laser systems can do that in pulsed mode but only with extremely low duty cycles. Getting enough power together to supply millions of homes would be tricky to say the least. (and see the note above about needing multiple probes just to be on the good side of probability)
- How does the probe survive decades of ultrahard radiation? What about dust it will encounter at high-subluminal speeds, also for decades? The shielding for that won't be lightweight, but the heavier the probe gets the more difficult it will be to accellerate.
- The satellite which is light enough to be powered by lasers also contains the most magical 3d printer anyone has ever seen. You can't just pull the molecules for advanced processors and energy generation equipment out of the air, such a probe would need to set up significant mining industries all on its own without any human interaction.
- A basic robot body. Keep in mind that "picking up a keychain and choosing the right key out of it without dropping the whole keychain" is already a challenge for modern robots.
In short, it'll be several centuries before humanity even gets close to such a project. I'd like to be wrong, but it seems extremely unlikely anyone of us will see such a thing in our lifetime.
It is very unlikely indeed, because we are not trying. We have a world set up so as to allow a few people to accrue wealth they couldn't possibly need, by impoverishing everyone else. Where are they going to make money out of this?
>but if it's just about you, the speed of light is no limitation at all
It's a huge limitation, even just getting propelled to "big enough speed", say 1/10 the speed of light.
We barely do 1/1500 the speed of light, in unmanned probes, and only because we sling shot on Solar gravity, not as propulsion or anything, and at 1400 o Celcius, plus deadly radiation, not to mention any micro-meteor as big as a particle of dust could kill someone there).
> It's a huge limitation, even just getting propelled to "big enough speed", say 1/10 the speed of light.
If you can't even get up to 1/10 the speed of light, then you wish the speed of light was a huge limitation, but it's actually not affecting you at all.
If the point argued is solely "the speed of light is a huge limitation" (and not: "getting anywhere near the speed of light is a big issue"), I'd say accepting that "even basic much lesser speed is a huge problem" is hardly a refutation of that. Nor is it an argument towards the feasibility of the actual feat being discussed (interstellar travel).
I guess you're technically correct though: the speed of light is not an issue, if 1/10th the speed of light is already unachievable.
Don't even need to do time dilatation - just make you lifetime longer by techjlnical means (ideally almost infinite) and you will be in the next star sumystem before you figure out how to exit your VIM session.
I don't think it's motivated pessimism so much as a shifting tastes and changes in media. There are tons of SF stories with starships in movies, games and streaming platforms. It just happens to be the case that fantasy is more popular then SF at the moment where books are concerned.
That would only rule out stories based on interstellar travel, which is a tiny subset of what you can do in space. After all, you'll just end up inside another solar system that won't be much different from ours. The planets will be in different orbits but there will most likely be an asteroid belt and the effects of temperature will remain the same even if the planets are in different temperature ranges from our planets.
If earth is big enough for fantasy, then the solar system is plenty big enough for science fiction.
If you wanted to watch hard science fiction I would recommend watching anthrofuturism on YouTube who focuses exclusively on the moon.
Our astrophysicists don't even know why the universe is expanding, don't know that Lambda CDM is correct, don't know if things are universally consistent, yet we're so damned sure this is it.
We don't even know that this isn't a simulation. Not non-falsifiable, sure. But we're convinced we're bound to this solar system with our crude tools and limits of detection.
One new instrument could upset our grand understanding and models. Maybe we should wait until they get better hardware to marry ourselves to their prognostications of the end of time.
During the postwar years of plenty, people stopped dreaming. We had bold dreams before WWII, but people stopped looking at how far we'd come and started comparing themselves to everyone else. We had no mortal enemy, tremendous wealth, and "keeping up with the Joneses" became the new operating protocol.
We have more than we did in the past. The manufacturing wealth of 1940-1970 was a fluke. The trade wealth of 1980-2020 was a fluke. We were upset over an unfair advantage that won't last forever. Even today we're still better off than a hundred years ago, yet everyone focuses on how bad things are.
Maybe a return to hardship will make us dream again.
It’s well understood that the expansion of the universe is not “due to general relativity”. General relativity does explain some details of that expansion.
The expansion of the universe is largely due to the impulse provided by the Big Bang. General Relativity does attempt to explain some details regarding what’s happened after the Big Bang, but provides no insight into the Big Bang itself. Nor does it offer insight into Dark Energy, a concept that Einstein opposed.
The universe is expanding due to general relativity... in the sense that Einstein literally wrote "... plus the expansion of the universe" into his equations.
It's also moaning about me coming from a datacentre IP (proxy) with some vague complaints about load introduced by AI crawlers. I think this guy treats "protecting" his site as a hobby.
Is there a reason we would need to coordinate on what to exchange rather than, say, beginning with encyclopedias and textbooks then moving to a constant stream of notable papers, news, discoveries, etc? What kind of bandwidth can you hit with a cooperating neighbour where improvements become civilisationally important? How many bytes (megabytes? Terabytes?) of meaningful new data does humanity produce per second? I suspect it's reasonably low.
Good question. My thought is similar to yours, but there is a lot of room for debate on what to send. They probably don't care about the roman empire like we do - but there are enough references in modern science that we need to send a summary just so they understand some things. We produce a lot of data, but most of it isn't meaningful.
if this is a real situation I wouldn't be asked. So use salt
I never quite got what was so "hot" about it. There seems to be an entire parallel ecosystem of corporates that are just begging to turn AI into PowerPoint slides so that they can mould it into a shape that's familiar.
One reason may be that it makes it a lot easier to open up a product to AI. Instead of adding a bad ChatGPT UI clone into your app, you inverse control and let external AI tools interact with your application and its data, thus giving your customers immediate benefits, while simultaneously sating your investors/founders/managers desire to somehow add AI.
I think using total parameters is fair, it correlates well with the RAM prerequisites to run it. Otherwise Kimi K2 would be "small" despite being a trillion parameters!
If I were to build something for Gemini models I'd plan around ingesting a bunch of context then oneshotting it.
reply