For Indian companies, a Zoho One yearly subscription is USD 13 a month if you use it for all your employees. That's USD 8000 a year if I have 50 employees, which I can straightaway claim as expenses and get a tax benefit out of it. And this includes CRM, Mail, chat, invoicing, accounting, marketing, advertising, etc. etc. So not just building the app, but also support, interoperatibility and offloading of all work which is not core of my business.
I doubt you'll get all this for $8K/year (India) or $22K (USA) even after you vibe-code once (not counting the ridiculous costs of developing with AI - you still need your engineers to do that even before you start running the token counter).
Garry somehow gave free publicity to Zoho with this post. Maybe that was his intention?
For regular consumers, Gemini's AI pro plan is a tough one to beat. The chat quality has gotten much better, I am able to share my plan with a couple more people in my family leading to proper individual chat histories, I get 2 TB of extra storage (which is also sharable), plus some really nice stuff like NotebookLM, which has been amazing for doing research. Veo/Nanobanana are nice bonuses.
It's easily worth the monthly cost, and I'm happy to pay - something which I didn't even consider doing a year ago. OpenAI just doesn't have the same bundle effect.
Obviously power users and companies will likely consider Anthropic. I don't know what OpenAI's actual product moat is any more outside of a well-known name.
Gemini also will answer most queries where ChatGpt won't do a lot of things. Example: "Create an image of Snow white". This will give the stand "Violates our content policy" even though the story was written hundreds of years ago. You can even point out the story is in the public domain and it still won't do it.
I strongly advise never using Google's Drive storage. They're known to scan all content, and to disable all access if even a single file is "problematic", often misclassified by a bot. If you do use the storage, do backup all your files, and be ready to lose access at any time, with no way to reach any intelligent human.
I agree with you 100%. We do syncs to another non-google storage account anyway, plus the google accounts are primarily for Android phone usage because photos and videos take up quite a big chunk of space now; they do not have any legitimately important files stored outside of photos sync and phone backups, so there is no deep loss if the account gets banned outside of some inconveniences.
Since we are on the topic of bans & Google, I have a question.
How likely or difficult is it for Google to engage in, for lack of better word, "thought policing"?
You ask your "private" AI assistant to answer a naughty question or help with problematic task(from Google's hidden list) and then you eventually face the ban hammer.
Did anybody ever get banned for searching the wrong keywords?
If Google is smart they'd ban Gemini access while leaving services like Gmail enabled because otherwise customers wouldn't trust them and would avoid Gemini.
I don't think there's any reports of banning from all Google services based on Gemini use.
Through my work I have access to Google's, Anthropic's, and OpenAI's products, and I agree with you, I barely touch OpenAI's models/products for some reason even though I have total freedom to choose.
Do you happen to know if the AI features of the Google One 5TB plan is equivalent to the 2TB AI pro plan? It is so difficult to understand what actually comes with their plans, and I want to have the 5 TB storage for backups.
Yeah it was an absolute nightmare trying to figure out the difference, and I still do not know the correct answer to this, and by the looks of it, neither does Google support, because they were as clueless as I was when I asked them about it.
One thing I read on a reddit thread [1] was that the AI pro 2 TB plan explicitly allows sharing the AI and storage benefits when you enable family sharing on them, while the 5 TB plan doesn't.
However, when I went to sign up, the 5 TB plan wasn't available at all! It's only their lite and basic plans (the one with 30 and 100 GB of storage); the 5TB one only showed up after I signed up for the pro plan, and judging by how the UX looked, you pay an extra amount on top of your AI pro plan.
Now I definitely need family sharing, but I don't need the full 2 TB, let alone 5 TB, so I didn't bother checking further about the 5TB plan.
Also, I am in India, maybe things are different in your region?
If we stop for a while and really consider the value of AI tools, then comparing them on price doesn't make much sense. Any of these tools give hundreds, thousands, or tens of thousands of dollars of value per month to the user. With that in consideration they should mostly be compared on quality.
> With that in consideration they should mostly be compared on quality
Take a look at the comments in the thread and tell me whether there is a consensus on which AI has the best "quality". Gemini, Claude, ChatGPT are all stochastic machines; they'll give me a different output at different times for the very same query, with differences in quality each time within themselves, let alone other products.
I did my own checks; newer Gemini's output is consistently "good enough" for me and my family now, we individually do not use the full extent of the Pro plan (collectively, we do), and NotebookLM is something which more than one of us uses everyday; Image generation is something we use once a week or so. Given all this, the feature breadth within Gemini covers all bases for us, with a significant catch-up in quality compared to earlier to a point that we don't really need to look elsewhere for now.
Plus, for us USD 20 is not a small amount; it's equivalent to one of our larger utility bills we need to pay for every month. So price is definitely an important point of consideration.
> Take a look at the comments in the thread and tell me whether there is a consensus on which AI has the best "quality".
I'm not saying there's any certain answer to which AI has the best quality. That answer depends on the user. For you, Gemini seems to fit the bill very well.
> Plus, for us USD 20 is not a small amount; it's equivalent to one of our larger utility bills we need to pay for every month.
That's not a logical comparison, since those things aren't related in any way. Your utility bill being cheap doesn't make everything else expensive. Some things are just great value, that doesn't mean everything else is not worth it. In that case, you should compare every other purchase and expense with that utility bill, and logically not spend money on anything else.
The same thing is true for a _ton_ of tech products. My home internet plan easily gives me more than $1000 in value per month. My cell phone hardware probably gives me $2000+ in value over even a short 2 year life. Customers still tend to choose the cheapest option that meets requirements.
If AI suddenly became $10k/month or even $1k/month, I would stop using it. It just doesn't provide that much value to me. If it did, I would probably find a way to use local models or some other approach to drive the cost down.
If home internet became $1k/month, I would pay it. $10k, no - I just don't have the cashflow to support that.
If I had to choose one of the three to give up, AI, home internet, or cellphone, I would give up AI. If I had to choose two, I'd give up my cell plan. Home internet is worth a ton of value and dollars to me.
Yes. It's not just the money; you'll be at the center of Google's power base. Spend a few years there, and it'll be much easier to move to anywhere in the world you want (within Google or otherwise).
Being at headquarters always makes it easier to move elsewhere. Being outside of headquarters makes it more difficult, because the main decision-makers are usually at HQ and you need fewer hops to reach them in order to get what you want.
Unless you're planning to stay in the valley permanently, I would not think too much about sprawl/car stuff. IMO there should always be painful disadvantages so that you have motivation to move towards where you really want to go :D
LOL in the name of security, HDFC is trying to move their OTP verification to be almost entirely app-only, (not open-source TOTP which can be generated by authenticator/any other auth app; you can only use HDFC's app for that even if you want to log in via desktop).
I think that’s pretty common worldwide. In Australia I’ve never encountered a bank or government service that allows any widely accepted secure 2FA. It’s always SMS or their own app. There used to be physical hardware tokens as well but they are going away.
I don't even care that much if they want to handle the 2FA with their proprietary methods. There are Android APIs that broker the OTP SMS delivery to the app without the app needing full access to the phone's messages.
If they can't do it on iPhone, they don't need to do it on Android.
You are thinking in the right direction; a lot of experienced developers are also thinking the same way.
The goal is not to become specifically a buggy-whip manufacturer or a specialist mill-worker; the goal is to have enough mental faculties and critical-thinking skills to adapt to any situation and be able to use any tool at hand to achieve your own goals and that of the employer.
Being a software architect means you actually need to gain depth in certain aspects of software development and computer science/engineering, and understand how an LLM works, what its weak points are, and to stop it from making mistakes. The point of double-majors is to expand your breath, not your depth.
You need both, depth and breadth, and thankfully LLM tools can help you in gaining both a lot quicker.
For some reason, I had the opposite effect due to AI - previously I enjoyed building things but hated the actual writing of code part. Now that AI can do that for me, I can keep my focus on the more important problems, and let AI deal with the lower-level stuff.
Your focus should be on gaining enough competence to solve hard problems by yourself, and in teams; and to learn how to learn. I would not worry too much about semantics of job roles - roles might change, but work (whatever that might be) will always be there, and you need to know how to do difficult types of work well.
You might be interested to know your comment caused Gemini 3 to go meta on this question. This is what I found in its thinking:
```
Evaluating Date Discrepancies
I've just uncovered a significant discrepancy: a "Hacker News" result flags a date error originating from the very format of parenthetical dates. The system appears to be misinterpreting these, leading to demonstrably false information. This warrants further investigation to understand the root cause and ensure data integrity.
Analyzing Date Ambiguity
I'm now grappling with the user's date. The Hacker News comment suggests the user's prompt might be flawed, as it contradicts the actual date of an event I've indexed. Specifically, the conference referenced occurred in October 2024, not September 2025 as the prompt implies. This leads me to question the user's understanding of the timeline or if the prompt refers to an unrelated event in September 2025. This inconsistency demands further clarification.
...
Investigating User Prompt Intent
I've just realized that the Hacker News snippet reveals this might be a specific problematic test prompt. My strategy is to focus on the October 2024 forum, a strong match, organized by Kattia Cambronero and CCT. I'll verify if there was a 2025 event, but the 2024 event fits the described "crisis" and "NGO coordination". If the user says "approx Sept 2025," they likely mean a recent event.
```
I tried both these prompts (along with the SINAC one as per GP) in Sonnet 4.5 and Gemini 3, and they both answered correctly for all three. Both also provided context on the chess question as well.
You might not believe this, but there are a lot of people (me included) that were extremely excited about the Gemini 3 release and are pleased to see the SOTA benchmark results, and this is reflected in the comments.
I definitely believe it--I'm not a total AI hater. The jump on the screen usage benchmark is really exciting in that it might substantially help computer-use agentic workflows.
That said, I think there is too much a pattern with recent model releases around what appears to me to be astroturfing to get to HN front page. Of course that doesn't preclude many organic comments that are excited too!
A bit of both always happens. But given how important these model releases are to justify the capex and levels of investment, I think it is pretty clear the various "front pages" of our internet are manipulated. The incentive is just too strong not to.
There are approximately 300 comments on the half dozen or so posts on the front page about Gemini at the moment. 2 threads reference AGI, one of them this one.
Perhaps I shouldn't have implied an expectation of lots of explicit mentions of "AGI". It is more the general sentiments being expressed, and the extent to which critical takes seem to be quickly buried.
I'm totally open to being wrong though. Maybe the tech community is just that excited about Gemini 3's release.
Not sure if this is agreeing or disagreeing with there being astroturfing.
But I'd reckon that the negative sentiments at the top, combined with that there are over eight Gemini 3 posts on the front page recently, is good evidence of manipulation. This actually might be the most posted about model release this year, and if people were that excited we wouldn't have negative sentiment abound.
Hasn't the president signed an executive order that says birthright citizenship is not for children of non-citizens? I see that it's being challenged in court, but the order is currently valid, right?
Executive orders cannot overrule the Constitution.
14th Amendment:
"All persons born or naturalized in the United States, and subject to the jurisdiction thereof, are citizens of the United States and of the State wherein they reside."
There are rumblings about "subject to the jurisdiction thereof" somehow excluding folks based on their immigration status, but frankly, the meaning is clear, and jurisprudence recognizes this. The jurisdiction carveout is for international diplomats, i.e. people who are literally not subject to US law. Immigrants, even illegal immigrants, are subject to US law. Stating otherwise would have vast repercussions.
> Executive orders cannot overrule the Constitution.
And I would hope this is a fairly universally held position, not so partisan. Today one side might cheer an executive order overriding the 14th amendment, but how will they feel if the next administration decides to pull the same stunt with the 2nd?
We don't want to go there. There are already some states experimenting with doing end-runs around the Constitution with their own civil laws, and for similar reasons I would expect rational people to want that effort to fail.
>> Executive orders cannot overrule the Constitution.
> I would hope this is a fairly universally held position, not so partisan.
I agree. I think the constitution limits both the executive and the legislative branches.
> how will they feel if the next administration decides to pull the same stunt with the 2nd?
The 2nd amendment has already been overridden by federal laws without a constutional amendment.
The 2nd used to mean that the states has a right to let their citizens arm themselves privately with military weapons. The federal government was forbidden by the 2nd to interfere with this.
I'm from Europe and fine with the very restrictive licensing we have here.
But it looks very shortsighted to wildly re-interpret the constitution far outside of the original meaning, instead of passing new amendments.
> The 2nd used to mean that the states has a right to let their citizens arm themselves privately with military weapons
In particular, at the time that it was written, it meant arm themselves with military weapons for the purposes of military action. That's what the contemporary use of the term "bear arms" was understood to mean. Try to find any mention of self-defense from back then. It wasn't what they were thinking about.
Or look at this earlier version: “A well regulated militia, composed of the body of the people, being the best security of a free state, the right of the people to keep and bear arms shall not be infringed, but no one religiously scrupulous of bearing arms, shall be compelled to render military service in person.”
That conscientious objector clause at the end certainly gives some context to the discussion.
The modern interpretation of the second amendment is very different.
> In particular, at the time that it was written, it meant arm themselves with military weapons for the purposes of military action. That's what the contemporary use of the term "bear arms" was understood to mean. Try to find any mention of self-defense from back then. It wasn't what they were thinking about.
That's what I meant too. I didn't bring up self-defense, did I?
The 2nd amendment protects the states' right to build up their own state militias by allowing their citizens to arm themselves with military weapons. It forbids the federal government from interfering with this.
> The modern interpretation of the second amendment is very different.
Yes. The federal "assault weapons ban" is completely incompatible with the 2nd amendment.
This was pushed through without a new amendment. Instead people used linguistic acrobatics to re-interpret the meaning of the 2nd amendment.
It would have been a lot easier today to shut down any attempts to re-interpret the 14th amendment if we hadn't started down this path with the 2nd.
Thanks for the detailed answer, I think that'll be a relief for many. However, would you say this still is a volatile situation for people who are facing this issue? Are the rulings _final_ on this? Or is there chance of people getting stuck in limbo?
> Thanks for the detailed answer, I think that'll be a relief for many. However, would you say this still is a volatile situation for people who are facing this issue? Are the rulings _final_ on this? Or is there chance of people getting stuck in limbo?
No, rulings are not final. SCOTUS could and very well may disagree with more than a hundred years of jurisprudence and overrule e.g. US v. Wong Kim Ark[1], enabling much easier denaturalization by the federal government. Here's an example article from a right-wing think tank about why they believe SCOTUS should overrule Ark[2].
That seems like a very good demonstration of the pitfalls of originalist interpretations of the Constitution. Even then, the argument comes off as extremely weak. And it doesn't even begin to try and address the consequences of reinterpreting the meaning of "and subject to the jurisdiction thereof".
Are conservatives envisioning a new class of slaves? People born on US soil who have none of the protections of the Constitution? Even if that is not the goal, it's not hard to imagine that there would be far-reaching consequences from deciding that the Constitution was not a limit on the behavior of government, but in fact only applied to citizens. What a massive bump in power for the bureaucrats in DC.
Heck, we could just snatch people off the street and declare they cannot prove they are a citizen therefore they have no Constitutional protections. No right to due process so they can prove they're a citizen, nothing like that. Better plan on carrying your passport at all times (and hope it doesn't get ... lost).
> Heck, we could just snatch people off the street and declare they cannot prove they are a citizen therefore they have no Constitutional protections.
I'm not sure if you intended this as a joke, but this is happening now, even if you do have proof of citizenship on you[1]:
> Congressman Bennie Thompson, ranking member of the House Homeland Security Committee, reported that “ICE officials have told us that an apparent biometric match by Mobile Fortify is a “definitive” determination of a person’s status and that an ICE officer may ignore evidence of American citizenship—including a birth certificate” when the app says a person is undocumented.
> Hasn't the president signed an executive order that says birthright citizenship is not for children of non-citizens?
Executive orders have force to the extent that they exert powers that the President has directly under the Constitution or that are assigned to the President by Congress exercising the powers it has directly under the Constitution.
Amending the Constitution by altering the definition of citizenship in the Fourteenth Amendment (or overruling the Supreme Court's consistent reading of the language of the Fourteenth Amendment, if you prefer that characterization) is neither a power granted to the President directly by the Constitution, nor a power Congress has granted the President by statute, nor even within the power granted to the Congress by the Constitution to grant to the President if it was inclined to do so.
> I see that it's being challenged in court, but the order is currently valid, right?
“Currently valid” is a tricky concept. In one sense, its is valid only to the extent it is actually compliant with the Constitution and laws which have higher priority than executive orders. Or you can read the question as really being about whether it can currently be applied, in which case the answer is a more simple “no”, because after the Supreme Court made the usual recent route to a simple single interim resolution pending the full litigation by simply deciding that nationwide injunctions were not within the power of district courts, they could only issue orders against government actions applicable to the litigants before them, a class action was certified covering everyone who might be affected by the order [0], and a preliminary injunction in that case has blocked the order.
No, it is held up in court. The SCOTUS tried to make it valid by ruling against universal injunctions, but within days the challenges were refiled as class actions.
I doubt you'll get all this for $8K/year (India) or $22K (USA) even after you vibe-code once (not counting the ridiculous costs of developing with AI - you still need your engineers to do that even before you start running the token counter).
Garry somehow gave free publicity to Zoho with this post. Maybe that was his intention?
reply