Hacker Newsnew | past | comments | ask | show | jobs | submit | Aliabid94's commentslogin

MMLU-Pro:

Gemini-3.1-Pro at 91.0

Opus-4.6 at 89.1

GPT-5.4, Kimi2.6, and DS-V4-Pro tied at 87.5

Pretty impressive


Funny how Gemini is theoretically the best -- but in practice all the bugs in the interface mean I don't want to use it anymore. The worst is it forgets context (and lies about it), but it's very unreliable at reading pdfs (and lies about it). There's also no branch, so once the context is lost/polluted, you have to start projects over and build up the context from scratch again.

The sheer number of bugs and lack of meaningful improvements in Google products is a clear counterargument to the AI bull thesis

If AI was so good at coding, why can’t it actually make a usable Gemini/AI Studio app?


I think Google might just be institutionally incapable of making good UX

Most of these tests are one-prompt in nature. I've also noticed issues with the PDF reader in Gemini which was very frustrating, although it is significantly better now than it was even two weeks ago. On the contrary, now GPT-5 seems to be giving me issues.

In my experience, Gemini is the most insightful model for hard problems (particularly math problems that I work on).


You know, with a bit of prompting, you can instruct Gemini to output the state of the conversation into a prompt that you can enter in a new chat and continue where you left off. But now with a fresh context window.

I gave up on Gemini 3.1 Pro in VSCode after 2 hours. They fully refunded me.

Yeah if I could use Gemini with pi.dev that would be my choice. But Gemini CLI is just so, so bad.

Gotta derail any peace talks!


Can't have Gaza have relief for a second!


What does this have to do with Gaza? One would think that if the IDF is busy in Iran, it will probably be less busy in Gaza.


Everything. A new conflict distracts from the ongoing genocide and allows its perpetrators to stay in power.


LOL. The US is on it too. So what you have to say for yourself now?


What peace talks? The ones where for over a year Iran refused to deescalate their nuclear war program and the now Europe range ballistic missiles?


You are lying, they have been trying to avoid this war in any possible way. But Israel wanted this war before they lost the support of the USA population (that it's happening fast) or they have a less accommodating USA president.


I agree about Israel fast losing support among the general public here but the idea of a less accommodating executive or legislative branch in the US for Israel is unthinkable. Not unless the system is changed from the ground up in dramatic fashion. The two most relevant branches of government in this country are completely beholden to Israel and anybody denying it is a zionist shill.


I can have an LLM generate a 10,000,000 article encyclopedia and be better than both!


Worth noting that a partner at Sequoia (Shaun Maguire) publicly accused the wrong guy of being the shooter.

https://www.fastcompany.com/91463942/sequoia-shaun-maguire-b...


> Maguire subsequently partially apologized for those comments in a video. “This tweet did not land the way I thought it would,”

What an asshole. He could have gotten the kid killed, not to mention the damage to his social reputation. And he can't even manage a "sorry if you were offended" non-apology.


The "did not land" video they're talking about, that was his response to people being mad at him for calling Mamdani an Islamist (and being "from a culture that lies about everything"). Also, "partially" is doing a lot of work there: he starts that video saying "cancel culture is alive and well" and doesn't in fact back off at all from his claim: the "did not land" part is even just Maguire lamenting that he accidentally helped Mamdani by targeting him.

Anyway, when he went after the Brown student saying he was "very likely" the shooter (also bringing in Mamdani again), he did less: he simply deleted the video.


Oh - thank you very much for the correction, I must have been reading the article too quickly!


Shaun Maguire has a long history of inflammatory comments and pushing false information on Twitter.

Every time he’s involved in a new scandal I’m surprised all over again that he’s still a partner and Sequoia still hasn’t pressured him to stop.


I'm impressed he hasn't been fired and sued into bankruptcy.


It's because they agree with him.


I can't express how puzzled I am that Maguire is still at Sequoia. Forget cancellation; anyone should be free to say whatever they want. This is about judgment, humility, discretion and dare I say empathy, which are fundamental skills in any investment process and which a partner at the most storied venture fund in the word ought to have.

In what world is it good or right to dox a random undergrad based on speculation, simply because maybe just maybe it will net you Internet points? Note that Maguire never apologized once it became clear he was wrong; he simply deleted the post. He gets to keep the engagement and outrage points and move on, paying no price for spreading a dangerous lie. The undergrad he and others doxxed can't say the same.

Shaun would be just another rage-baiter if it wasn't for the Sequoia imprimatur. With an investor like this on your cap table, who needs enemies? It shouldn't matter if Shaun is the "Elon guy" at Sequoia or indeed the best investor in the world. Integrity should and does precede returns in time. But maybe I am naive and this just isn't true for megacap venture as an asset class, where so much depends on sidling up to the 50 or 100 founders who can reliably produce decacorns to return your fund.

Perhaps all we can do is vote with our feet. Sequoia is on my cap table today, but if I was fortunate to have the choice between them and a similar firm that actually demonstrated integrity instead of just talking about it, I would not take money from them again. In all likelihood they won't care a whit about me, but they may care more about some of you, reading this.


> This is about judgment, humility, discretion and dare I say empathy, which are fundamental skills in any investment process

I'm sorry, don't take this the wrong way, did you smoke pcp before writing this?



The whole VC industry is poison at this point.


It's like a lottery for rich people.


Why are you downvoted? VC's mostly give money to rich kids from prestigious schools. VC's basically hate the poor and want nothing to do with them.


[flagged]


I'm mostly surprised that someone can so consistently and repeatedly demonstrate an inability to filter information he receives and still be trusted with LPs' money. It's another form of Gell-Mann amnesia.


Rich guys are mainly incompetent. They'll tell you they're rich because of meritocracy, but I've found that too much money has the opposite effect. You end up surrounded by yes-men and can buy your way out of any failure, so your skills (if you ever had em) atrophy.


[flagged]


Everyone knows sequoia can't invest... but this is too far

> Maguire, acting as a self-appointed digital detective, has shared posts suggesting that an entirely different man was behind the crimes—a Palestinian student at Brown University...

> On July 4, Maguire made inflammatory comments calling New York City Mayor-elect Zohran Mamdani an “Islamist.”

Jokes aside, maguire does seem like an emphatically despicable person


[flagged]


Unvelievably's current comment says

  >> Maguire clearly "comes from a culture that lies about everything."
But given yours, did they originally say what you quoted?

I'm trying to understand the downvotes and if people think you said what they said


Everyone is talking in some kind of weird in-group code or in-jokes that I can't understand so I'll decipher it for the rest of us normies.

> Maguire clearly "comes from a culture that lies about everything."

This is a reference to Shaun Maguire's Twitter post where he said that Zohran Mamdani "comes from..."

https://x.com/shaunmmaguire/status/1941135110922969168

> > Maguire is Jewish, with ancestral ties to early Jewish settlers in California.

> Sir, we are going to have to ask you to leave.

This comment appears to be reacting to the first one by assuming the first one is saying that Jewish people lie about everything, and it responds by saying this is unacceptable to say.

I have been off Twitter for 2 months and when I go there I can't understand anything. People are always saying "can I say something?" and "we know what this means" and shit like that and either the 2 months have killed my brain or something because I never know what the first guy isn't going to say and the second guy knows.

Now Hacker News is similarly incomprehensible and I'm starting to think my mind is no longer able to handle human speech. If this is happening to anyone else, then I hope the interpretation helped. If it didn't, then maybe I'm just losing my mind.


Thanks for the explanation -- I also had no idea what this meant.

I am disturbed that in-group code has been normalized as a way to state socially abhorrent positions out in the open, as if it offered plausible deniability.


I hate everyone involved in this. It’s like a confluence of every type of perma-victim with immense privilege.


Claude summary:

Key Findings:

Trump-Epstein relationship:

Epstein frequently discussed Trump in emails, calling him "the worst person" he'd ever met with "not one decent cell in his body" Despite this, evidence shows ongoing contact, including Epstein visiting Trump Tower a week after the 2016 election Epstein's pilot tracked Trump's movements to Palm Beach Epstein claimed to know "how dirty Donald is" and called him "borderline insane"

Continued elite associations:

Despite Epstein's 2008 sex offense conviction, prominent figures maintained contact:

Peter Thiel: Discussed meetings with Woody Allen and dinners together

Steve Bannon: Extensive correspondence about European politics, think tanks, and strategy sessions

Ehud Barak: Collaborated on Syria-related op-eds

Troubling journalist relationships:

Landon Thomas Jr. (NY Times): Advised Epstein on PR strategy and requested "photos of donald and girls in bikinis"

Michael Wolff: Consulted Epstein while writing books about Trump, sought his input on framing him as credible


How did you generate this?


Trump was the only one that testified against Epstein and witnesses, under oath, stated he wasn't with any of the girls on the island.

Esptein hating him is a good thing as I don't really think we should trust someone like him as a judge of character.


Seeing how trump has a colossal ego and loves to “win”, wouldn’t it makes sense for him to champion their release, exonerating himself completely, giving him a huge win and an opportunity to rub it in everyone’s face? Why is he fighting against their release so very, very hard?


> under oath

Cute that you think it matters to Trump.


First one to snitch gets the best deal. Question is do you honestly think Trump wouldn't do something like that?. I don't need Epstein to tell me what type of person Trump is. Or should I stop believing my lying eyes?.


Feels unnecessarily jingoistic, China succeeding will not come at our expense. Unlike the US, they don’t want to project their values across the globe.

Who’s working on gene editing for IQ maxxing?


> Unlike the US, they don’t want to project their values across the globe

Tell that to Pakistan, Taiwan, Cambodia, Korea and checks notes Tibet.


Don't forget most of Africa, where it's a lot of "Oh, so sorry you got in massive debt to us for that clean water system. You know, a nice Chinese naval base would look great right over there."


Or, "how about you let us exploit your natural resources from now on."


The CIA was operating for a long time in Tibet and got the Dalai Lama kicked out. Taiwan wouldn't even exist if it weren't backed by forgeign powers, namely the US and UK. The US dropped 2.7 million tons of bombs on Cambodia. The US has conducted thousands of drone strikes in Pakistan, and of course, they fought a war in Korea.


> CIA was operating for a long time in Tibet and got the Dalai Lama kicked out

Nobody contests that the U.S. projects power and culture globally.

> Taiwan wouldn't even exist if it weren't backed by forgeign powers, namely the US and UK

…this is true for most countries on the planet. Including the US and UK.

> US dropped 2.7 million tons of bombs on Cambodia. The US has conducted thousands of drone strikes in Pakistan, and of course, they fought a war in Korea

How is this relevant to whether China projects its culture?


China does not project it's power across the globe. You only listed countries China can literally spit on from within it's own borders.


> China does not project it's power across the globe. You only listed countries China can literally spit on from within it's own borders

China's projects power into the Red Sea and Central Asia, and is building bases to project further into the Persian Gulf, the Gulf of Thailand, South Atlantic and Coral Sea. (Also ironic to reference Tibet and China's borders in the same sentence. In imperial terms, China, Indonesia, Libya and Russia stand alone in having annexed by force, since WWII, the sovereign land of other nations that weren't their colonisers.)

Examples of cultural projection outside Asia are rarer, given Chinese power projection as a whole is newer, but one would expect to see--as it's happened in its vicinity, as it happened in America's vicinity first--Chinese-language and cultural institutions following economic interests. (It's already happening, but not significantly enough yet to be of note. Most current objections from locals are around the migration and settlement of ethnic Chinese workers in their communities.)


I get what you are saying but this is still pretty local.


> this is still pretty local

America’s cultural projection was similarly local while the British Empire reined.


Vietnam?


Tell it to the countries that don't exist anymore ...

Hong Kong, Xinjang (yep, that was a country), and the very barely kind-of existing Tibet and Mongolia.


They have territorial disputes with their neighbors, that’s not the same as trying to project their cultural values globally.

What dispute do they have with Pakistan? You mean India?


Look into the various instructions they have in other countries, that's before we get to Belt & Road


> What dispute do they have with Pakistan

You’re the one who straw manned to territorial disputes!

Beijing culturally projects in Pakistan. Capitalism with Chinese characteristics, a growing prevalence of Mandarin being taught as a second language [1], requiring Islamabad embrace Beijing’s foreign policy, et cetera.

(To be clear, this seems fine. Both Pakistan and Russia have proven dangerously incompetent as fully sovereign states. Perhaps being under Beijing is more stable and prosperous.)

[1] https://global.chinadaily.com.cn/a/202210/19/WS634f462aa310f...


Larry Ellison getting TikTok from the govt at just $14B is the biggest steal. His control of Paramount and CBS makes him the biggest owner of American attention, and he’ll have Bari Weiss steering it.


I like the idea! In my opinion (looking at SF) it’s still too low resolution. SF in particular can vary greatly in safety, walkability, etc. even a few blocks over within a neighborhood.


Because 1) this is not their own citizens they are surveilling and 2) Israel is committing genocide according to many (most?) international and human rights orgs, which would make Microsoft an accomplice


Considering microsoft disabled the emails of people who spoke out about palestinian human rights this is quite transparently a saving face tactic. They've been wilfully complicit at every step of the way.


The US, UK, EU, and Australia all surveil non citizens. It isn’t an issue for any one of them. They don’t even care that they’re doing warrantless surveillance of their own citizens.


“Jordan this week said they were told that Israel had prohibited filming Gaza from above.” Prohibiting reporting of a war zone should be seen as automatic confession of war crimes


Aerial photography is also used for targeting strikes, it is de facto prohibited in Ukraine, and most hot wars.


Israel is the only one performing air strikes in Gaza surely? So that's not a rationale reason for banning aerial photography here.

The obvious one is to hide the destruction of civilian areas.


By Ukraine, not by Russia. Significant difference.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: