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

Gemini 3

blog.google

Post reply on HN
Print view View original

741–750 of 1001 posts

Re: Gemini 3

#741

Post by WhyOhWhyQ »

oezi wrote: post #501
epolanski wrote: post #464

Earlier quoted context omitted.

Imho Gemini 2.5 was by far the better model on non-trivial tasks.

To this day, I still don't understand why Claude gets more acclaim for coding. Gemini 2.5 consistently outperformed Claude and ChatGPT mostly because of the much larger context.

I'm not sure about this. I used gemini and claude for about 12 hours a day for a month and a half straight in an unhealthy programmer bender and claude was FAR superior. It was not really that close. Going to be interesting to test gemini 3 though.

Re: Gemini 3

#742

Post by jeswin »

pclmulqdq wrote: post #466
qsort wrote: post #450

Earlier quoted context omitted.

I'm not explaining myself right. Stockfish is a superhuman chess program. It's routinely used in chess analysis as "ground truth": if Stockfish says you've made a mistake, it's almost certain you did in fact make a mistake[0]. Also, because it's incomparably stronger than even the very best humans, sometimes the moves it suggests are extremely counterintuitive and it would be unrealistic to expect a human to find the…

Yeah, it is often pointed out as a brilliance in game analysis if a GM makes a move that an engine says is bad and turns out to be good. However, it only happens in very specific positions.

> Yeah, it is often pointed out as a brilliance in game analysis if a GM makes a move that an engine says is bad and turns out to be good.

Do you have any links? I haven't seen any such (forget GM, not even Magnus), barring the opponent making mistakes.

Re: Gemini 3

#743

Post by antonvs »

TechDebtDevin wrote: post #710
MaximusLegroom wrote: post #700

Earlier quoted context omitted.

Rooting is useless. We should be taking conscious action to reduce the bosses' manipulation of our lives and society. We will not be saved by hoping to sabotage a genuinely useful technology.

How is it useful other than for people making money off token outout. Continue to fry your brain.

They’re fantastic learning tools, for a start. What you get out of them is proportional to what you put in.

You’ve probably heard of the Luddites, the group who destroyed textile mills in the early 1800s. If not: https://en.wikipedia.org/wiki/Luddite

Luddites often get a bad rap, probably in large part because of employer propaganda and influence over the writing of history, as well as the common tendency of people to react against violent means of protest. But regardless of whether you think they were heroes, villains, or something else, the fact is that their efforts made very little difference in the end, because that kind of technological progress is hard to arrest.

A better approach is to find ways to continue to thrive even in the presence of problematic technologies, and work to challenge the systems that exploit people rather than attack tools which can be used by anyone.

You can, of course, continue to flail at the inevitable, but you might want to make sure you understand what you’re trying to achieve.

Re: Gemini 3

#744

Post by plaidfuji »

syspec wrote: post #364

I have "unlimited" access to both Gemini 2.5 Pro and Claude 4.5 Sonnet through work. From my experience, both are capable and can solve nearly all the same complex programming requests, but time and time again Gemini spits out reams and reams of code so over engineered, that totally works, but I would never want to have to interact with. When looking at the code, you can't tell why it looks "gross", but then you ask…

I have the same experience with Gemini, that it’s incredibly accurate but puts in defensive code and error handling to a fault. It’s pretty easy to just tell it “go easy on the defensive code” / “give me the punchy version” and it cleans it up

Re: Gemini 3

#745

Post by ivape »

lairv wrote: post #293

Out of curiosity, I gave it the latest project euler problem published on 11/16/2025, very likely out of the training data Gemini thought for 5m10s before giving me a python snippet that produced the correct answer. The leaderboard says that the 3 fastest human to solve this problem took 14min, 20min and 1h14min respectively Even thought I expect this sort of problem to very much be in the distribution of what the mo…

So when does the developer admit defeat? Do we have a benchmark for that yet?

Re: Gemini 3

#746

Post by ethmarks »

giarc wrote: post #642
ethmarks wrote: post #243

Earlier quoted context omitted.

The point of prediction markets isn't to be fair. They are not the stock market. The point of prediction markets is to predict. They provide a monetary incentive for people who are good at predicting stuff. Whether that's due to luck, analysis, insider knowledge, or the ability to influence the result is irrelevant. If you don't want to participate in an unfair market, don't participate in prediction markets.

But what's the point of predicting how many times Elon will say "Trump" on an earnings call (or some random event Kalshi or Polymarket make up)? At least the stock market serves a purpose. People will claim "prediction markets are great for price discovery!" Ok. I'm so glad we found out the chance of Nicki Minaj saying "Bible" during some recent remarks. In case you were wondering, the chance peaked at around 45% and…

I agree that the "will [person] say [word]" markets are stupid. "Will Brian Armstrong say the word 'Bitcoin' in the Q4 earnings call" is a stupid market because nobody a actually cares whether or not he actually says 'Bitcoin', they care about whether or not Coinbase is focusing on Bitcoin. If Armstrong manipulates the market by saying the words without actually doing anything, nobody wins except Armstrong. "Will Coinbase process $10B in Bitcoin transactions in Q4" is a much better market because, though Armstrong could still manipulate the market's outcome, his manipulation would influence a result that people actually care about. The existence of stupid markets doesn't invalidate the concept.

Re: Gemini 3

#747

Post by brcmthrowaway »

ogig wrote: post #711

I just gave it a short description of a small game I had an idea for. It was 7 sentences. It pretty much nailed a working prototype, using React, clean css, Typescript and state management. It event implemented a Gemini query using the API for strategic analysis given a game state. I'm more than impressed, I'm terrified. Seriously thinking of a career change.

To what?

Re: Gemini 3

#748

Post by bgwalter »

ivape wrote: post #745
lairv wrote: post #293

Out of curiosity, I gave it the latest project euler problem published on 11/16/2025, very likely out of the training data Gemini thought for 5m10s before giving me a python snippet that produced the correct answer. The leaderboard says that the 3 fastest human to solve this problem took 14min, 20min and 1h14min respectively Even thought I expect this sort of problem to very much be in the distribution of what the mo…

So when does the developer admit defeat? Do we have a benchmark for that yet?

According to a bunch of philosophers (https://ai-2027.com/), doom is likely imminent. Kokotajlo was on Breaking Points today. Breaking Points is usually less gullible, but the top comment shows that "AI" hype strategy detection is now mainstream (https://www.youtube.com/watch?v=zRlIFn0ZIlU):

AI researcher: "Just another trillion dollars. This time we'll reach superintelligence, I swear."

Re: Gemini 3

#749

Post by xlbuttplug2 »

variadix wrote: post #693
knowriju wrote: post #674

Earlier quoted context omitted.

ARC-AGI has a hidden private test suite, right ? No model will have access to that set.

I doubt they have offline access to the model, i.e. the prompts are sent to the model provider.

Even if the prompts are technically leaked to the provider, how would they be identified as something worth optimizing for out of the millions of other prompts received?

Re: Gemini 3

#750

Post by stephc_int13 »

riku_iki wrote: post #689
energy123 wrote: post #683

Earlier quoted context omitted.

The 'private' set is just a pinkie promise not to store logs or not to use the logs when the evaluator uses the API to run the test, so yeah. It's trivially exploitable. Not only do you have the financial self-interest to do it (helps with capital raising to be #1), but you are worried that your competitors are doing it, so you may as well cheat to make things fair. Easy to do and easy to justify. Maybe a way to make…

they have two sets: - semi-private, which they use to test proprietary models and which could be leaked -private: used to test downloadable open source models. ARG-AGI prize itself is for open source models.

My point is that it does not matter if the set is private or not.

If you want to train your model you'd need more data than the private set anyway. So you have to build a very large training set on your own, using the same kind of puzzles.

It is not that hard, really, just tedious.

Post reply on HN