That docs page has a link in the first primary section on the page. Sure, it could be a huge CTA, but this is a docs page, so it's kinda nice that it's not gone through a marketing make over.
* besides sponsored result for AI Studio
(Maybe I misunderstood and all the complaints are about billing. I don't remember having issues when I added my card to GCP in the past, but maybe I did)
I've to this day never been able to pay for Gemini through the API, even though I've tried maybe 6-7 times
If you bring it up to Logan he'll just brush it off — I honestly don't know if they test these UX flows with their own personal accounts, or if something is buggy with my account.
This is my experience as well in my personal account, however at work given we were already paying for Google Cloud it was easy enough to connect a GCP account.
But somehow personally even though I'm a paying Google One subscriber and have a GCP billing account with a credit card, I get confusing errors when trying to use the Gemini API
To Logan's credit though, his team made and drove a lot of good improvements in AI studio and Gemini in general since the early days.
I feel his team is really hitting a wall now in terms of improvements, because it involves Google teams/products outside of their control, or require deep collaboration.
Yes, I get the impression he has been fighting this fight internally since the day he arrived. He can’t exactly talk about how infuriating it must be, but I look forward to his memoir.
I could've made my comment more clear. Definitely missing a statement along the lines of "and then after creating, you click 'set up billing' and link the accounts in 15 seconds"
I did edit my message to mention I had GCP billing set up already. I'm guessing that's one of the differences between those having trouble and those not.
AI Studio is meant to be the fast path from prompt to production, bringing billing fully into AI Studio in January will make this even faster! We have hundreds of thousands of paying customers in production using AI Studio right now.
Every aspect is at least partially broken several times a day, and even when there isn't a temporary outage of something somewhere, there are nonsensical "blocks" for things that ought to just work.
I've been using the AI Studio with my personal Workspace account. I can generate an API key. That worked for a while, but now Gemini CLI won't accept it. Why? No clue. It just says that I'm "not allowed" to use Gemini Pro 3 with the CLI tool. No reason given, no recourse, just a hand in your face flatly rejecting access to something I am paying for and can use elsewhere.
Simultaneously, I'm trying to convince my company to pay for a corporate account of some sort so that I can use API keys with custom tools and run up a bill of potentially thousands of dollars that we can charge back to the customer.
My manager tried to follow the instructions and... followed the wrong ones. They all look the same. They all talk about "Gemini" and "Enterprise". He ended up signing up for Google's equivalent of Copilot for business use, not something that provides API keys to developers. Bzzt... start over from the beginning!
I did eventually find the instructions by (ironically) asking Gemini Pro, which provided the convenient 27 step process for signing up to three different services in a chain before you can do anything. Oh, and if any of them trigger any kind of heuristic, again, you get a hand in face telling you firmly and not-so-politely to take a hike.
PS: Azure's whatever-it-is-called-today is just as bad if not worse. We have a corporate account and can't access GPT 5 because... I dunno. We just can't. Not worthy enough for access to Sam Altman's baby, apparently.
> I've been using the AI Studio with my personal Workspace account. I can generate an API key. That worked for a while, but now Gemini CLI won't accept it. Why? No clue. It just says that I'm "not allowed" to use Gemini Pro 3 with the CLI tool. No reason given, no recourse, just a hand in your face flatly rejecting access to something I am paying for and can use elsewhere.
Passing along this feedback to the CLI team, no clue why this would be the case.
Excuse me? If you mean AI Studio, are you talking about the product where you can’t even switch which logged in account you’re using without agreeing to its terms under whatever random account it selected, where the ability to turn off training on your data does not obviously exist, and where it’s extremely unclear how an organization is supposed to pay for it?
Yes, much like admin.google.com (the GSuite admin interface), which goes ahead and tries to two-factor your personal GMail account every single time you load it instead of asking you which of the actual GSuite accounts you're signed into you'd like to use...
Yeah, with multiple chrome profiles, you have to be mindful of which one you last had focused before clicking a link from an external application (i.e. tailscale), so that it opens the new tab in the right instance so the account(s) you use in it are available
Def use multiple chrome profiles if you aren't. You can color code them to make visual identification a breeze
I'm aware of multiple Chrome profiles and I do not want to use them. Google should simply make their account switching consistent across their apps and work sensibly in these corner cases.
"simply" is doing a lot of work, profiles is the outcome of addressing the problems you are talking about. Many people enjoy them and find them useful. Why are you against using them?
Simply isn't doing much work, account switching works just fine on GMail, search, maps, calendar etc. The issue is that some Google apps do not follow the standard of the overall fleet. Google gives us the account switching feature, it's obviously an intended way to use their products. Otherwise they would not give you that and tell you to use browser profiles.
I don't want my history, bookmarks, open tabs and login sessions at every website divided among my 5 GSuite workspace accounts and my 1 personal Gmail. That adds a bunch of hassle for what? The removal of a minor annoyance when I use these specific Google apps? That is taking a sledge hammer to a slightly bent nail.
If it works for you, great, that's why it's there. But doing this for anything more than the basic happy path setup of "I have one personal account and 1 GSuite work account" is nuts in my opinion.
I always have a buggy ass hell experience with having multiple google accounts pretty much across all their services. I've been wondering if its just me or how the hell this is normal.
Don't get me wrong, aistudio is pretty bad and full of issues, but getting an apikey was not hard or an issue itself. Using any auth method besides personal account oauth with gemini-cli never worked for me after hours of trying
Python is the primary implementation, Java is there, Go is relatively new and aiming for parity. They could have contributed the Typescript implementation and built on common, solid foundation, but alas, the hydra's heads are not communicating well
These other "frameworks" are (1) built by people who need to sell something, so they are often tied to their current thinking and paid features (2) sit at the wrong level. ADK gives me building blocks for generalized agents, whereas most of these frameworks are tied to coding and some peculiarities you see there (like forcing you to deal with studio, no thanks). They also have too much abstraction and I want to be able to control the lower level knobs and levers
ADK is the closest to what I've been looking for, an analog to kubernetes in the agentic space. Deal with the bs, give me great abstractions and building blocks to set me free. So many of the other frameworks want to box you into how they do things, today, given current understanding. ADK is minimal and easy to adjust as we learn things
ADK is anything but minimal. It indeed has too much abstraction. It's certainly designed to promote Google's own services. If you are looking for lightweight frameworks, consider smolagents or Pydantic AI. Even OpenAI Agents SDK is simpler. LangChain/LangGraph are the epitome of incompetent designs.
These projects are all a level above open router, they call the same standard APIs, or even custom ones and manage the translation. They do a lot more as well
ADK has an option to use litellm (openrouter alternative), among many options
I have a claude max subscription and a gemini pro sub and I exclusively use them on the cli. When I run out of claude max each week I switch over to gemini and the results have been pretty impressive -- I did not want to like it but credit where credit is due to google.
Like the OP others I didn't use the API for gemini and it was not obvious how to do that -- that said it's not cost effective to develop without a Sub vs on API pay-as-you-go, so i do no know why you would? Sure you need API for any applications with built-in LLM features, but not for developing in the LLM assisted CLI tools.
I think the issue with cli tools for many is you need to be competent with cli like a an actual nix user not Mac first user etc. Personally I have over 30 years of daily shell use and a sysadmin and developer. I started with korn and csh and then every one you can think of since.
For me any sort of a GUI slows me down so much it's not feasible. To say nothing of the physical aliments associated with excessive mousing.
Having put approaching thousands of hours working with LLM coding tools so far, for me claude-code is the best, gemini is very close and might have a better interface, and codex is unusable and fights me the whole time.
> it's not cost effective to develop without a Sub vs on API pay-as-you-go, so i do no know why you would
My spend is lower, so I conclude otherwise
> I think the issue with cli tools for many is...
Came from that world, vim, nvim, my dev box is remote, homelab
The issue is not that it is a CLI, it's that you are trying to develop software through the limited portal of a CLI. How do you look at multiple files at the same time? How do you scroll through that file
1. You cannot through a tool like gemini-cli
2. You are using another tool to look at files / diffs
3. You aren't looking at the code and vibe coding your way to future regret
> or me any sort of a GUI slows me down so much it's not feasible.
vim is a "gui" (tui), vs code has keyboard shortcuts, associating GUI with mouse work
> Having put approaching thousands of hours working with LLM coding tools so far, for me claude-code is the best, gemini is very close and might have a better interface, and codex is unusable and fights me the whole time.
Anecdotal "vibe" opinions are not useful. We need to do some real evals because people are telling stories like they do about their stock wins, i.e. they don't tell you about the losses.
Thousands of hours sounds like your into the vibe coding / churning / outsourcing paradigm. There are better ways to leverage these tools. Also, if you have 1000+ hours of LLM time, how have you not gone below the prepackaged experience Big AI is selling you?
I did this same thing and this was my first result too. I am just not seeing how the author ended up where they did, unless knowing how to use Google search is not a core skill.
Read the full post. Partway down you will see they agree with you that getting an API key is not hard.
Paying is hard. And it is confusing how to set it up: you have to create a Vertex billing account and go through a cumbersome process to then connect your AIStudio to it and bring over a "project" which then disconnects all the time and which you have to re-select to use Nano Banana Pro or Gemini 3. It's a very bad process.
It's easy to miss this because they are very generous with the free tier, but Gemini 3 is not free.
I did notice in their post instead of searching for answers, they asked Gemini how to do things, and when that didn't work, they asked Claude.
I often see coworkers offload their work of critical thinking to an AI to give them answers instead doing the grunt work nessecary to find their answers on their own.
This rhetoric worries me. If you insist on degrading others at least fix it to something like:
> [They seemingly] can't think on their own without an AI [moderating]
They _literally_ can think on their own, and they _literally_ did think up a handful of prompts.
A more constructive way to make what I assume to be your point would be highlighting why this shift is meaningful and leaving the appeal to ego for yourself.
I agree with your assessment, I am in the wrong here. It's easy to be extra judgmental to anonymous figures on a blog you'll never meet. Thank you for reminding me to give people the benefit of doubt and not jump to worst case assumptions.
Low energy afternoons you might be able to come up with a prompt but not the actual solution.
There are people offloading all thoughts into prompts instead of doing the research themselves and some have reached a point where they lost the ability to do something because of over AI use.
During peak hours (4-9pm daily) in San Diego you can be paying nearly $1/kWh (generation + transmission cost) to SDGE, so at least in certain areas, the running cost is very much relevant even for consumers.
Agreed. They accomplished a lot with distillation and optimization - but there's little reason to believe you don't also need foundational models to keep advancing. Otherwise won't they run into issues training on more synthetic data?
In a way this is something most companies have been doing with their smaller models, DeepSeek just supposedly* did it better.
The military isn’t allowed to shoot down drones in the US. There was a WSJ story last month about drones flying over Langley for 2 weeks. All the general could do is stand on the roof and watch
They shot down at least 3 including one that 100% belonged to a local club, meaning the military had no clue what they were launching missiles at. One was shot down over Lake Huron, and the pilot actually even managed to miss the balloon with his missile. It's like 99 Red Balloons meets Idiocracy.
Obviously the military can shoot down whatever they want, let alone use EM tech, which is highly effective at grounding drones. Drones keep getting sighted near the exact areas that would be testing out drone militarization, and not getting shot down. Gee, I wonder who's they might be.
People would be so dramatically more informed if they dropped social media and corporate news.
1) there was a very public delay to shoot down anything even remotely above people. They just aren’t going to shoot something down over a city
From the WSJ article I mentioned:
“ Federal law prohibits the military from shooting down drones near military bases in the U.S. unless they pose an imminent threat. Aerial snooping doesn’t qualify, though some lawmakers hope to give the military greater leeway”
2) as you probably know, the pilot doesn’t really guide the missile…calling the pilot an idiot just clearly shows you have an axe to grind. Also, it’s not like the seekers are calibrated to take out balloons.
3) regarding EW - the tech is obviously still evolving and not always deployed
“ U.S. officials said they didn’t know who operated the drones in Nevada, a previously unreported incursion, or for what reason. A spokeswoman said the facility has since upgraded a system to detect and counter drones.”
Also, it is certainly possible to harden drones against EW as is being done in Ukraine on an evolving basis
Just think rationally - in one case you had completely harmless weather balloons, and the government completely freaked out, scrambled fighters and even recklessly launched missiles at them.
Here you have supposedly car sized drones operating, in large numvers, in high risk areas and the government response is nonexistent. Nearby flights have not even been diverted as they do when there's the slightest security risk in an area.
Check any radiation map to see what's probably happening. Parts of New York, in the vicinity of the sightings, are showing extremely high radiation levels.
Its probably just drones searching for the source with the secrecy aimed at trying to avoid a mass panic.
Looking at the history of the one counter currently showing elevated levels (northjerseymike), it looks like the current value is well within variance of historical levels. I jumped back 10, 50, and 100 pages and without plotting, it didn't seem anything is notable about more recent data.
Also... why wouldn't the feds just say they're inspecting infrastructure and avoid the entire question...?
IMO this is almost certainly a commercial LIDAR mapping effort plus right wing conspiratorial hysteria.
The pages are sorted by date... I ended up going back roughly 1 month, 3 months, 6 months, and 12 months.
A single value at a moment in time doesn't mean anything at all. You need to see the variance over time. And you need to trust the source data. The only "dangerously high" readings I saw were from counters that had no name, no history, no identifier, no additional values.
This theory makes no sense from the get-go and this "evidence" is extremely low quality.
Ok so you went back a day, saw the ongoing sky high readings from multiple sources which you were apparently trying to claim didn't exist, now acknowledge they exist, and now you want to claim they don't mean anything. Ok.
I do challenge you to show me the law stating that the military cannot engage unidentified and non-responsive potentially hostile vessels breaching controlled airspace, let alone with full authority from the CIC. That's just about the dumbest talking point ever.
Though even if such law exists, which it doesn't, then like any law in modern times, or even increasingly the Constitution, if the political establishment deemed it inconvenient then they would simply ignore it, and make up some lies.
And on that note, they are now acknowledging that they are indeed drones. The 'its just airplanes' lie lasted about 5 minutes. These people seriously hold the public in contempt.
Why can't your dad keep using his existing computer? Sure, if you make your living on the computer the new laptops are great. But if he's just checking email, photos, etc - I don't know why his computer needs to become a paperweight
At some point you no longer get security upgrades. Or new web browser versions aren't available and you're unable to access certain sites. In some cases there are workarounds like installing an open source OS but that's too much hassle for most consumers.
Specifically because in each case, no updateable web browser was available any longer. To have your main machine increasingly unable to render web pages, and to suffer growing security vulnerabilities, pretty much bricks the machine for any purpose other than a scanning workstation, etc.
Fair :) I was overlooking that this latest computer could be an older intel machine that didn't receive the latest OS, thus won't still still have years of security only updates.
Apple had good reasons for both transitions. In the scheme of 'forced upgrades' these are about as good as you're going to get. Also, if the OPs dad is using the computer for so little that it would last another 30 years, they certainly have no need to upgrade computers. No reason one can't keep using an intel iMac to browse the web
Yes, I'm not claiming that is true formal reasoning, but it is certainly more of a chain of thought than was previously being done and does indicate that some questions require more and less "thought"
For anyone curious to hear more about how this happens, and a discussion with someone who was a former police officer (maybe even detective?) yet still fell victim, The Daily did an episode on this in April as well
In general, I've seen lots of 'victim blaming' with these sorts of scams. I mean, I do understand that it's easy to sit there and think 'I understand sending money the first time, but how do you still fall for it the 6th time they ask you to send more money?'. But I think it's important to remember that victims are often older or new to the country*. These scams are designed and refined to make you feel trapped.
* I'm aware the OP involves a Canadian couple and the NYT story involves an American couple. I don't think the direct country matters. Most of these scams are all about scaring and isolating someone.
Timeshares themselves are already shady, and there are many people desperate to offload them.
Also, there are psychological biases at play too, regardless of whether you are older or newer to the country. One of key bias in the engine that runs scams and cons is that, once you have done something for someone, you are more likely to keep doing things for them. Even knowing this does not really inoculate you to that effect.
Ebay is full of timeshare listings for next to nothing (if you don't consider even paying the annual fees isn't worth it in most cases).
Years back my GF got roped into a timeshare presentation because she wanted free nights in a hotel room. After gently scolding her I printed off pages of Ebay timeshare listings and went to the presentation with her. What a high pressure scam. Anyway, we stayed the required time and when the guy took us off to "close the deal" I whipped the listings out of my pocket and said "Look at this! I can get a better deal on a better resort for $1!". The poor salesman just stood there with his mouth opened then finally said they would have our complimentary tickets at the desk thanks for attending.
My wife and I signed. It was exhausting. I did a token effort at looking at the contract and found the recension clause they had to include as required by law. When I asked about it, the way everyone else froze in that moment and then tried to downplay it stuck in my mind, but we were too exhausted and finished the paperwork.
Immediately upon walking out and got to a local restaurant, my wife and I looked at each other and knew we made a mistake. We ended up looking up how to give notice for the recension and was able to execute it (even though their office was closed for the weekend; it was a good thing I've written and executed business contracts before). (For those curious, you state that you are giving notice of recension for the new property; and then you send it in at least three different ways in accordance to the contract, and get paper trail for each of those ways to prove that you sent them).
It's how I knew about how people get trapped into this through property laws that normally protect property owners.
Since then, I've let myself get impolite at timeshare salesmen. The high pressure sales start at those tables, even before you get invited for the pitch. They abuse the tendency for civil people to be polite and redirect civility to continue the pitch. (And the slickest of them will guilt trip you on being nasty to explain yourself ... at which they can keep pitching ...)
We get free vacations by sitting through timeshare presentations. The trick is to get the timeframe in writing before you go. And to only tell them your name, and repeating the phrase, "we will not sign any contract or agreement."
Literally say nothing else.
We've been to Cancun, Hawaii, Minnesota, and Colorado for weeks for free doing this.
Usually there's a penalty on top of the cost of the hotel.
You really have to be selective, and read the fine print, though. Often they try to make you pay fees for the free room, and the fees almost equal the cost of the room. Read everything, and be sure you can say no to people before you even think about doing this.
I like toying with them as well. Got some tickets and tours from 30 min playing with those goofballs. But it’s not for the faint of heart. My wife plays the good cop and I am the bad cop. Even though I am soft spoken and kind of shy. They don’t know what to make of us and just throw the whatever they’ve promised at us look away in the end.
I've been told the other trick is to turn to your spouse and say "I don't know honey, we would have to sell the RV". They know people never sell the RV and so they will let you out the door as it is a waste of their time. (You don't need an RV, you just need them to think you have an RV.)
Note if you are thinking about an RV, rent them. A timeshare is a better deal than buying an RV for most people, even though timeshares are scams and RVs are not.
Another example, although less palatable, is beggers. Not the obvious poor kind but the ones that approach you at a parking lot or gas station, with some sob story while being dressed relatively neat and not "hobo" like. They abuse polite good nature ontop of the guilt. As a young adult I realized I can't help everyone in the world and learned to tell them no. As an older adult I unfortunately don't even look their way anymore and just shake my head. They know what this means and like a good shakedown artist they move on to the next mark because it's a numbers game.
The stats here in South Africa are shocking. Some beggars here make more money than genuine workers. And they even have "turf wars" over the lucrative begging spots and busy intersections.
Good for you to get out of it in time! I nearly got tricked into signing myself, but did a bit of research during a bathroom visit, had the contract in front of me, and stopped myself when I saw the same red flags in the contract that people warned about online.
Small vocabulary correction: the term for what you did to get out of it, and the clause that allowed you to do so, is recission, not recension.
We went to a pitch once since we got like $100 or something. We had 0 intention of signing anything since we are of the opinion time shares at worst are a scam and at best just not for us. The sales guy was so pushy it was comical. I finally stopped him:
“I want to be clear, we aren’t buying this. We have 0 intent here”
He looked at me puzzled and said:
“Why would you waste an hour of your vacation? For $100? You’re just wasting your vacation for that?!”
Getting really upset and slightly personal. I had to respond
“We wanted to see how big a scam these really are and I can’t believe you find suckers that sign on”
He was pretty upset and said the front desk has our gift and huffed out.
> Since then, I've let myself get impolite at timeshare salesmen. The high pressure sales start at those tables, even before you get invited for the pitch. They abuse the tendency for civil people to be polite and redirect civility to continue the pitch. (And the slickest of them will guilt trip you on being nasty to explain yourself ... at which they can keep pitching ...)
Treat them as you would any other predator, like a lion, a grizzly bear, or a mugger. Because that's what they are.
Did you pause to wonder if you could think of even a single way of behaving that would be equally appropriate when confronted with a timeshare salesman as with a mugger, or with a grizzly bear?
I mean, I guess running away as fast as you can would technically count but in that case I'd suggest there are more fun ways to get exercise and easier ways to get rid of an annoying salesman...
Yeah I also got dragged into one of those while on vacation in a timeshare property in exchange for some tour tickets. The tactics are truly despicable. They insisted that me and my wife shouldn't talk to each other in our language because "it's not polite". We didn't speak the local language very well (although we could understand it), so this was obviously to keep us from talking to each other and be more vulnerable. They tried to waste as much of our time as possible in the hopes that we just sign the damn contract to get rid of them and enjoy our vacation.
I'd never heard of timeshare back then, but luckily the deal sounded really bad anyway and we were very adamant on not making any decisions under pressure even if it meant losing this "once in a lifetime offer". In the end they begrudgingly gave our tickets to the tours and ushered us out.
The real reason people "fall" for these pressure scams is that law enforcement will not help protect the victim against the predator, but because the victim is upstanding citizen but the predator is not, the predator or law enforcement will harm the victim if the victim tries to actively defend themselves against the predator.
You can be not gullible, and they will find some way to get at you. Like to argue? They will jujutsu that. Think you are too intelligent to fall for this? They'll use that. If you find a trick that works, they learn and adapt.
Best way is to walk away. Easier said than done for a lot of people.
Robert Greene has a book about this. In one of the examples, he talked about a scammer trying to scam Henry Ford. Ford had no imagination. The scammer failed. Most people are not a Henry Ford.
I sold cars for a decade in the SV area. The amount of times I've seen engineers, lawyers, accountants, doctors and higher level executives make errors is pretty high. No one is 100% ON all the time.
The amount of times I watched very financially conscious people explain to me that they want to lease and then buy their vehicle afterwards, yet forget about sales tax during the buyout after lease end is comical. They were always surprised that even with a high money factor a lease to purchase still paid off...... Depending on how nice they were I would sometimes show them what the forgot.
I remember reading that there were entire product lines that omit you ever bought one mail order you were forever on the lists of “suckers who buy nose hair trimmers mail order” and they passed those lists around like candy.
'I understand sending money the first time, but how do you still fall for it the 6th time they ask you to send more money?'.
I think that falls under the "sunk cost fallacy". Like they are thinking "Well, I've invested so much money already and I'm so close to the payoff now, I may as well send a little more"
I listened to that podcast. I remember being really frustrated with the ex-cop and thinking there were so many red flags. I wonder if it really unfolded as presented.
> I mean, I do understand that it's easy to sit there and think 'I understand sending money the first time, but how do you still fall for it the 6th time they ask you to send more money?'.
Such an assumption would show a clear lack of empathy, no? Esp. on HN where nearly all are familiar with data-mining and relentless targeting of people based on data.
Time share companies are notoriously aggressive in their sales pitch. So "the set of people who bought time shares" already selects for people who have a much higher propensity to send money to these scammers, even multiple times. And upon being scammed, they probably also get their data sold to hundreds other scammers and get stuck in a recursive loop of scam attempts at a much higher rate than the average HN-er.
The linked release mentions trusted users and links to the usage tier limits. Looking at the pricing, o1-preview only appears for tier 5 - requiring 1k+ spend and initial spend 30+ days ago
That's a very dismissive and unrealistic statement. There are plenty of investors investing in things such as AI and crypto out of FOMO who either see something that isn't there or are just pretending to see something in the hope of getting rich.
Obviously, there are plenty of investors who don't fall into this situation. But lets not pretend that just because someone has a lot of money or invests a lot of money that it means they know what they are doing.
I suppose my phrasing was a bit harsh at the end. To be clear, I mean that it doesn't mean they know what they are doing on every investment. Investing misses happen! People are wrong!
I google `gemini API key` and the first result* is this docs page: https://ai.google.dev/gemini-api/docs/api-key
That docs page has a link in the first primary section on the page. Sure, it could be a huge CTA, but this is a docs page, so it's kinda nice that it's not gone through a marketing make over.
* besides sponsored result for AI Studio
(Maybe I misunderstood and all the complaints are about billing. I don't remember having issues when I added my card to GCP in the past, but maybe I did)