Hacker Newsnew | past | comments | ask | show | jobs | submit | throwaw12's commentslogin

Can we switch from Claude Code to Google yet?

Benchmarks are saying: just try

But real world could be different


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.


Its not just subpar, its not even sub-sub-par.

It goes into loops and never completes a task 8 times out of 10 that i've used it.


It's not just the tooling. If you use Gemini in opencode it malfunctions in similar ways.

I haven't tried 3.1 yet, but 3 is just incompetent at tool use. In particular in editing chunks of text in files, it gets very confused and goes into loops.

The model also does this thing where it degrades into loops of nonsense thought patterns over time.

For shorter sessions where it's more analysis than execution, it is a strong model.

We'll see about 3.1. I don't know why it's not showing in my gemini CLI as available yet.


welcome to AI-SEO

Now OpenAI will build its own search indexing and PageRank


you are looking at 2023 and 2024, FOMO started late 2024 and beginning of 2025

Do you know where there are any numbers to back this up though?

This was an interesting read: https://gizmodo.com/right-to-compute-laws-are-spreading-acro...

this part in particular:

Like right-to-work laws that frame themselves as protecting individual freedom, critics warn that right-to-compute statutes could, in practice, primarily benefit large corporations by limiting the ability of states and local governments to regulate AI projects.


The Montana law is also nearly identical to model legislation drafted by the American Legislative Exchange Council, meaning it could easily be replicated by lawmakers elsewhere.

Alec which is the group that formed after business/ultra wealthy decided it was cheaper to just buy government than work for votes for unpopular things after the Powell Memorandum.

It was super effective! https://eml.berkeley.edu/~saez/SaezZucman14slides.pdf


Did you reply to the wrong message? I asked for statistics showing significant increases in electricity usage due to AI data centers.

why creates a law if there is no electricity impact?

as I am getting older, I wholeheartedly relate to what you are saying.

1. Some people give a damn, but decision makers won't give them money and resources to fix. Good enough is enough, lets work on next project.

2. Inviting "real people" is expensive, A/B testing is cheaper

3. Complicated 150 page, 120 tab ERP or B2B SaaS can be funded, simple things -> investors are worried that it can be replicated by 1 engineer with Claude Code/Codex at hand

4. Have a heart --- this makes me think, unfortunately we lost it to capitalism. We are even ready to ruin our kids life and their mental health, if it makes money to us

Sad sad sad


If possible I would love to have another button in HN: "Probably AI Slop"

when collected enough points, eventually punishes the authors and every comment they write will be labeled as "AI Slop"


I'm all for it if it'll stop people from commenting about things being AI slop or vibecoded and comes with a new guideline discouraging said comments.

Fair enough. If the substance reads generic, that’s on me.

The intent wasn’t to produce volume, it was to frame the economic layer of the discussion. Whether written with or without AI assistance, the argument still stands or falls on its logic.

What’s more interesting to me is how quickly “AI slop” becomes shorthand for structured reasoning. As these tools become common, separating low-effort output from thoughtful analysis is going to matter more, not less.

Ironically, this ties back to the original question about bubbles. If AI-generated content becomes abundant and cheap, signal will only survive where there’s clear economic or technical grounding behind it.

I’m spending a lot of time thinking about that boundary right now, especially in developer-facing systems where quality and constraint adherence actually matter. The difference between fluff and production-grade behavior is becoming very measurable.

Curious how others here distinguish between shallow AI-assisted output and work that’s actually grounded in systems thinking.


There must be a misunderstanding.

I'm saying I dislike the constant "this is AI slop" and "this is vibecoded" complaints on posts. I see no value in them and I wish they'd stop.

I'm saying nothing about the use of AI in generating content.


> Palantir gives the health data to government

Ice cream was sellers when they were selling it, but not the data, data belongs to someone else, who didn't explicitly allow selling it


The problem with today's society is you walk into a hospital bleeding and they make you sign an ultimatum.

Legally this should be treated as signing under duress and invalidated.

If someone's life or well-being depends on it, and undergoing services in not a choice, terms and conditions should not be legally allowed to be unilaterally dictated by one party.


Fun fact: it’s illegal to open new hospitals without the permission of the government.

There are multiple layers of corruption at work here. (They also cap the number of doctors, and clinics, etc).


> it’s illegal to open new hospitals without the permission of the government.

This doesn't seem surprising on its face given that a hospital is, not unreasonably, a heavily regulated entity.


“on its face” is doing the heavy lifting here. Banking is highly regulated but you don’t need government permission to open new branches. The food supply chain is heavily regulated but you don’t need government permission to start new restaurants.

The supply of medical care, from operating rooms to doctors themselves, is heavily controlled by the state. There are billions, perhaps trillions of dollars that would flow into reducing the cost and increasing the availability of high quality medical care in the US if this were not so.

The demand is through the roof and will continue to rise. But the right to supply is only handed out to cronies.


> Banking is highly regulated but you don’t need government permission to open new branches.

The closer economic unit would probably be a bank itself, and to my understanding you do effectively need the government’s permission to open one of those.


> don’t need government permission to start new restaurants

Zoning, construction permits, occupancy permits, patio permits, food licenses, liquor licenses, health inspections, dumpster permits, etc


All of those are normal things for operating any business, and are not limited in the usual case.

Liquor licenses notwithstanding.

There is no default-deny for getting a business license or opening a restaurant in a commercially zoned area, anyone can do it. Licensing and permission aren’t quite the same thing.


> It would not be a good idea because the goal of companies are not to get you to consume only what you need, they want you to consume more.

It's good exactly because of this. Every company is pushing us to consume more, and Wall Street is at the top of this, growth at all costs (including human lives, mental health, just anything)

Only way to save Earth is to stop the Wall Street greed machine.

We should be making shoes which lasts 4 years, clothes which last at least 2 years with no "fashion" industry pushing us to change it every 2 days.


Where are the 8% annual returns going to come from to pay for all the defined benefit pensions and retiree healthcare plans?

Not trying to pick apart your point but I rotate a small set of staple clothes and they’re in fine condition after two years (haven’t had much time for clothes shopping since toddler arrived), despite me abusing “quick wash” and “drycare 40c” constantly on Miele W1/T1 stack for “90 minute, good to fold” laundry.

I don’t buy the cheapest brands, but also don’t buy anything marketed as premium/luxe.

Mostly I gravitate towards stuff with a fairtrade cotton (and good thread count, but that’s from preference of how it feels to wear)

Plus, I may be deluded but I’m of the opinion that polo shirts and jeans/neutral trousers are a multi-decade winning combination.


I might add, I've had some pretty long lasting clothes with Gildan heavy weight 100% cotton, and a few wool shirts I rotate. I think there are a few tricks that I accidently stumbled on to making my clothes last a long time: Firstly, I use mild detergents, and usually set the machine to "tap cold". I haven't noticed that my clothes are less clean. Secondly, I usually air dry on a rack instead of a dryer. I was forced to do this when I lived in an apartment, and suspect that this is a big factor. Thirdly, and maybe the most important, I spent some time learning what colors I look best in. Turns out there is quite a rabbit hole you can go down in terms of styling your clothes to match not what you "like" but what compliments your skin tone, body shape, and so on.

I actually think the last point has been profound, because I rarely _feel_ like buying clothes, because I look good in whatever Is in my closet.

For reference, I cycle through about 7 t-shirts. I wear the same one in the gym. I have a pair of rotten clothes for when I'm farming or hunting, but my daily clothes endure more daily wear and tear than urban living for sure.


> Only way to save Earth is to stop the Wall Street greed machine.

Wall Street here is a boogie man.

Using resources to make life better is actually good. And we keep getting better at it, and doing so in more sustainable and efficient ways.

And if it’s not - you fundamentally believe technology is not beneficial. Then all of industrial society needs to be reversed.


making low quality items that wear out quickly and influencing people to over consume just so big businesses profit more is not "using resources to make life better"

wall street != technology.

exactly. wall street here is a personification of "bad effects of industrial society"

Shoes which last 4 years and clothes which last 2 years are widely available, if you want them. They're not particularly expensive. But many consumers prefer to buy less robust items that won't hold up to daily wear and then complain about longevity.

> But the original repository has almost 4,000 stars, and surely, 4,000 developers can’t be wrong?

This is such a negative messaging!

Let's check star history: https://www.star-history.com/#forrestchang/andrej-karpathy-s...

1. Between Jan 27th and Feb 3rd stars grew quickly to 3K, project was released at that time.

2. People star it to be on top of NEW changes, people wanted to learn more about what's coming - but it didn't come. Doesn't mean people are dumb.

3. If OP synthesized the Markdown into a single line: "Think before coding" - why did he went through this VS Code extension publishing? Why can't they just share learnings and tell the world, "Add 'Think before coding' before your prompt and Please try for yourself!"

PS: no I haven't starred this project, I didn't know about it. But I disagree with the authors "assumptions" about stars and correlating it to some kind of insight revelation


I just packaged the extension for the fun of it! And I do want people to try for themselves, that is the point. About people that are not dumb; surely many people are not dumb; many people are very smart indeed. But that does not prove there are no dumb or gullible people!

thanks for responding and sharing your perspective.

What I would say, you could have omitted some negativity or judgement from your post about 4k devs starring something because it looks simple, because they might have different intentions for starring.

Here is another great example of 65K "not wrong" developers: https://github.com/kelseyhightower/nocode - there is no code, long before AI was a trend, released 9 years ago, but got 65K stars! Doesn't mean devs "not wrong", it means people are curious and saving things "just in case" to showcase somewhere


Nocode is obviously a banter repo and people starred it because made them laugh.

I wonder if someone could explore creating a standalone product out of that markdown, just for the fun of it.

Perhaps a cool wall art sticker? "In this house we don't assume. We don't hide confusion. We surface tradeoffs."

Let's start a company and raise money from investors!!

Unfair competition.

Should western models go through similar regulatory question bank? For example about Epstein, Israel's actions in Gaza, TikTok blocking ICE related content and so on?


As I promised earlier: https://news.ycombinator.com/item?id=46781777

"I will save this for the future, when people complain about Chinese open models and tell me: But this Chinese LLM doesn't respond to question about Tianmen square."

Please stop using Tianmen question as an example to evaluate the company or their models: https://news.ycombinator.com/item?id=46779809


Neither should be censoring objective reality.

Why defend it on either side?


> Neither should be censoring objective reality.

100% agree!

But Chinese model releases are treated unfairly all the time when they release new model, as if Tianmen response indicates that we can use the model for coding tasks.

We should understand their situation and don't judge for obvious political issue. Its easy to judge people working hard over there, because they are confirming to the political situation and don't want to kill their company.


That's just whataboutism. Why shouldn't people talk about the various ideological stances embedded in different LLMs?

Why do we hear censorship concerns only when it comes Chinese models? Why don't we hear similar stances when Claude or OpenAI releases models?

We either set the bar and judge both, or don't complain about censorship


I think more people should spend time talking about this with American models, yeah. If you're interested in that then maybe that can be you. It doesn't have to be the same exact people talking about everything, that's the nice thing about forums. Find your own topic that American models consistently lie or freeze on that Chinese models don't and post about it.

I don't want to criticise models for things they're not being trained on or constraints companies have. None of the companies said our models don't hallucinate and we always have right facts.

For example,

* I am not expecting Gemini 3 Flash to cure cancer and constantly criticising them for that

* Or I am not expecting Mistral to outcompete OpenAI/Claude on their each release, because talent density and capital is obviously on a different level on OpenAI side

* Or I am not expecting GPT 5.3 saying anytime soon: Yes, Israel committed genocide and politicians covered it up

We should set expectations properly and don't complain about Tianmen every time when Chinese companies are releasing their models and we should learn to appreciate them doing it and creating very good competition and they are very hard working people.


I think most people feel differently about an emergent failure in a model vs one that's been deliberately engineered in for ideological reasons.

It's not like Chinese models just happen to refuse to talk about the topic, it trips guardrails that have been intentionally placed there, just as much as Claude has guardrails against telling you how to make sarin gas.

eg ChatGPT used to have an issue where it steadfastly refused to make any "political" judgments, which led it to genocide denial or minimization- "could genocide be justifiable" to which sometimes it would refuse to say "no." Maybe it still does this, I haven't checked, but it seemed very clearly a product of being strongly biased against being "political", which is itself an ideology and worth talking about.


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

Search: