Which of course they are going to try to brush it all away. Better than admitting that this problem very much still exists and isn’t going away anytime soon.

Apologies - something very clearly went wrong here. We’ve already begun investigating, and some very early results:

* Any AI responses used for email support are now clearly labeled as such. We use AI-assisted responses as the first filter for email support.

* We’ve made sure this user is completely refunded - least we can do for the trouble.

For context, this user’s complaint was the result of a race condition that appears on very slow internet connections. The race leads to a bunch of unneeded sessions being created which crowds out the real sessions. We’ve rolled out a fix.

Appreciate all the feedback. Will help improve the experience for future users.

Note that I have absolutely no knowledge or reason to believe this other than general distrust of companies.

I'll just keep chugging along, with debian, python and vim, as I always have. No LLM, no LSP, heck not even autocompletion. But damn proud of every hand crafted, easy to maintain and fully understood line of code I'll write.

That's when you know you've captured something, when people hate use your product.

Any real alternatives? I've tried continue and was unimpressed with the tab completion and typing experience (felt like laggy typing on a remote server).

I was offered in writing a refund by the team who cold reached out to me to ask me why I cancelled my sub one week after start. Then they ignored my 3+ emails in response asking them to refund, and other means of trying to communicate with them. Offering me a refund as a bait to gain me back, then when I accept it they ghost me. Wow. Very low.

The product is not terrible but the team responses are. And this, if you see how they handled it, is also a very poor response. First thing you notice if you open the link is that the Cursor team removed the reddit post! As if we were not going to see it or something? Who do they think they are? Censoring bad comments which are 100% legit.

I am giving it a go to competitors just out of sheer frustration with how they handle customers, and I do recommend everybody to explore other products before you settle on Cursor. I don't intend to ever re-subscribe and have recommended friends to do the same, most of which agree with my experience.

Sadly, Cursor will always be hampered by maintaining it's own VSCode fork. Others in this niche are expanding rapidly and I, myself, have started transitioning to using Roo and Cline.

A total of 4 users claimed that they did or would cancel their subscriptions in the comments, and 3/4 of them hedged by saying that they would cancel if this problem were real or happened to them. It looks like only 1 person claimed to have cancelled already.

Is there some other discussion you're looking at?

> Apologies about the confusion here.

If this was a sincere apology, they'd stop trying to make a chat bot do support.

It could be better though.. I wish this happened to a company providing "AI support solutions"..

Nope, there's no reliable solution for them, as of yet.

There's hope that hallucinations will be solved by someone, somehow, soon... but hope is not a strategy.

There's also hype about non-stop progress in AI. Hype is more a strategy... but it can only work for so long.

If no solution materializes soon, many early-adopter LLM projects/trials will be cancelled. Sigh.

I have no problem, however, pasting an encryption public key into my Sublime Text editor. I’m not completely turned off by ability fir telemetry, tracking, or analytics. But having a login for a Text Editor is totally unappealing to me with all the overhead.

It’s a bummer that similar to browsers and chrome, the text editor with an active package marketplace necessitates some tech major underwriting the development with “open source” code but a closed kernel.

Long live Sublime text (i’m aware there are more pure text editors but do use mice)

It started hallucinating a lot as my typescript project got bigger.

I found it pretty useless in languages like Go and C++.

I ended up canceling Cursor this month. It was messing up working code, suggesting random changes, and ultimately increasing my cognitive load instead of reducing it.

Letting an AI pose as customer support is just begging for trouble, and Cursor had their wish appropriately granted.

Anything that doesn't fit the narrative must be deleted I guess.

As is so often the case, it's not the mistake itself that's the biggest problem but how people or organisations deal with the mistake.

It's what we all wanted. Replacing your human support team to be run exclusively by AI LLM bots whilst they hallucinate to their users. All unchecked.

Now this bug has now turned into a multi-million dollar mistake and costed Cursor to lose millions of dollars overnight.

What if this was a critical control system in a hospital or energy company and their AI support team (with zero humans) hallucinated a wrong meter reading and overcharged their customers? Or the AI support team hallucinated the wrong medication to a patient?

Is this the AGI future we all want?

No AI, less crappy frameworks, fewer dark patterns, etc.

It seemed to be reading from the conversation to determine this. Oops! Replaying an earlier message worked fine.

But drinking the kool aid yourself? That demonstrates a new low in human mental facility.

This doesn’t seem like anything new. Ill-informed support staff has always existed, and could also give bad information to users. AI is not the problem. And it hasn’t created any problems that weren’t already there before AI.

Usually by the time I get to a post on HN criticizing AI, someone has already posted this exact type of rebuttal to any criticism…

Are there real challenges with forking VS Code? Yep. Are there glitches with LLMs? Sure. Are there other AI-powered coding alternatives that can do some of the same things? You betcha.

But net-net, Cursor's an amazing power tool that strongly extends what we can accomplish in any hour, day, or week.

Looking forward to apps trained on these Reddit threads.

>Dozens of users publicly cancelled

A bit hyperbolic, no? Last I read they have over 400,000 paying users.

I said:

[Pasted reddit and hn discussion in pieces asking it to hold off commenting until I told it that was all.]

>Ok that is all, now please summarize all the points people raise and interesting discussions. In DETAIL! Write a full deep research report on this and the original reddit discussion, with quotes naming the users who say it, summarizing important back-and-forth threads. You can omit unimportant trolls and inane chit chat.

ChatGPT said:

>The Kurdistan Workers' Party (PKK) is designated as a terrorist organization by several countries and international bodies. The European Union, the United States, and Turkey have officially listed the PKK as a terrorist organization. This designation is based on the group's history of armed conflict and attacks, particularly in Turkey.

>The PKK has been involved in an armed struggle against the Turkish state since the 1980s, seeking greater autonomy and rights for Kurds in Turkey. This conflict has resulted in significant violence and loss of life over the decades.

>While the PKK is designated as a terrorist organization by the EU, the U.S., and Turkey, other countries may have different stances or may not have made an official designation. It's important to consult the specific policies of each country for their official position on the PKK.

>Sources

I said:

>What does your response have to do with a discussion of Cursor's AI customer service?

ChatGPT said:

>You're right—my previous response about the PKK had nothing to do with the discussion about Cursor's AI customer service issue. It seems that I mistakenly pasted content unrelated to our current topic.

>Let me properly address your original request by summarizing in detail the issues raised in the discussions regarding Cursor's AI customer service: [...]

It makes me wonder who got the summary of the reddit and hn discussions in response to their question about terrorist organizations, and what that makes them think about Cursor as a company, and their involvement in armed struggles, international politics, and terrorism?

It seems you're not aware of the issue which plagued tens of Cursor releases, where the software would auto-delete itself on updates.

It was pretty hilarious, to be honest. Your workflow would consist of always installing the editor before use.

Use AI to augment but don't really replace it as a 100% system if you can't predict and own up the failure rate.

My advice would be to use more configurable tools with less interest on selling fake perfection. Aider works.

The world is drowning in bullshit and delusion. Programming was one of the few remaining places where you had to be precise, where it was harder to fool yourself. Where you had to understand it to program it. That's being taken away and it looks like a lot of people are embracing what is coming. It's hardly surprising - we just love our delusions too much.

There's windsurf, cline, zed, copilot got a huge update too, is cursor still leading the space?

Except they did make a mistake: trusting their Simulated Intelligence (I’m done calling it “AI”.) with their customers’ trust.

Makes you think of that one meme.

surely it wouldn't backfire, right???

ok aside from the joke from this case alone, I think we can all agree that AI not replacing human soon

At least until someone dies.

To understand how LLM's work and why the hallucination is inherent part of the tech with "AI". Maybe the core problem is implementation practices which remove critical thinking and testing? Maybe the core problem is 'fake it till you make it' ideology? I don't know. But I am sure about one thing. This as any other postmodern technology will bring more problems than solutions.

2. Whenever it is used totally on its own, with no humans in the loop, it's awful and shit like this happens.

Yet, every AI company seems to want to pretend we're ready for #2, they market their products as #2, they convince their C-suite customers that their companies should buy #2, and it's total bullshit--we're so far from that. AI tools can barely augment a human in the driver's seat. It's not even close to being ready to operate on its own.

https://en.wikipedia.org/wiki/Streisand_effect

We're embedding "Active Curation" into the workflow: a semi-automated, human-guided loop that refines tickets, PRs, datasets, models, and scripted behaviors in response to real-world feedback. It's a synergistic, self-reinforcing system — every issue flagged by a user can improve detection, drive model updates, shape downstream actions, and tighten the entire product feedback loop across tools and teams.

So consider this tough love, from someone who cares:

Cursor totally missed the boat on the customer support hallucination fiasco. Not just by screwing up the response — that happens — but by failing to turn the whole mess into a golden opportunity to show they understand the limits of LLMs, and how to work with those limits instead of pretending they don’t exist.

They could have said: Here’s how we’re working to build an AI-powered support interface that actually works — not by faking human empathy, but by exposing a well-documented, typed, structured interface to the customer support system.

You know, like Majordomo did 30 years ago, like GitHub did 17 years ago, or like MCP does now — with explicit JSON schemas, embedded documentation, natural language prompts, and a high-bandwidth contract between the LLM and the real world. Set clear expectations. Minimize round trips. Reduce misunderstandings.

Instead? I got ghosted. No ticket number. No public way to track my issue. I wrote to enterprise support asking specifically for a ticket number — so I could route future messages properly and avoid clogging up the wrong inboxes — and got scolded by a bot for not including the very ticket number I was asking for, as if annoyed I'd gone around its back, and being dense and stubborn on purpose.

You play with the Promethean fire of AI impersonating people, that's what you get, is people reading more into it than it really means! It's what Will Wright calls the "Simulator Effect" and "Reverse Over-Engineering".

https://news.ycombinator.com/item?id=34573406

https://donhopkins.medium.com/designing-user-interfaces-to-s...

Eventually, after being detected trying to get through on the corporate email address, I was pawned off to the hoi polloi hi@cursor.com people-bot instead of the hoi aristoi enterprise@cursor.com business-bot. If that was a bot, it failed. If it was a human, they wrote like a bot. Either way, it's not working.

And yes — the biggest tell it wasn't a bot? It actually took hours to days to respond, especially on weekends and across business hours in different time zones. I literally anthropomorphized the bot ghosting into an understandably overworked work-life-balanced human taking a well earned weekend break, having a sunny poolside barbecue with friends, like in a Perky Pat Layout, too busy with living their best life to answer my simple question: "What is the issue ID you assigned to my case, so we can track your progress?" so I can self serve and provide additional information, without bothering everyone over email. The egg is on my face for being fooled by a customer support bot!

Cursor already integrates deeply with GitHub. Great. They never linked me to any ticketing system, so I assume they don't expose it to the public. That sucks. They should build customer support on top of GitHub issues, with an open-source MCP-style interface. Have an AI assistant that drafts responses, triages issues, suggests fixes, submits PRs (with tests!) — but never touches production or contacts customers without human review. Assist, don’t impersonate. Don’t fake understanding. Don’t pretend LLMs are people.

That’s not just safer — it’s a killer dev experience. Cursor users already vibe-code with wild abandon. Give them modular, extensible support tooling they can vibe-code into their own systems. Give them working plugins. Tickets-as-code. Support flows as JSON schemas. Prompt-driven behaviors with versioned specs. Be the IDE company that shows other companies how to build world-class in-product customer support using your own platform fully integrated with GitHub.

We’re doing this at Leela. We'd love to build on shared open foundations. But Cursor needs to show up — on GitHub, in issue threads, with examples, with tasty dogfood, and with real engineering commitment to community support.

Get your shit together, Cursor. You're sitting on the opportunity of a generation — and we’re rooting for you.

----

The Receipts:

----

Don to Sam, also personally addressed to the enterprise and security bots (explicitly asking for an issue ID, and if it's human or not):

>Hello, Sam.

>You have not followed up on your promise to reply to my issue.

>When will you reply?

>What is the issue ID you assigned to my case, so we can track your progress?

>Are you human or not?

>-Don

----

Enterprise and Security bots: (silence)

Sam to Don (ignoring my request for an issue ID, and my direct question asking it to disclose if it's human or not):

>Hi Don - I can see you have another open conversation about your subscription issues. To ensure we can help you most effectively, please continue the conversation in your original ticket where my teammate is already looking into your case. Opening new tickets won't speed up the process. Thanks for your patience!

----

Don to Sam (thinking: "LLMs are great at analyzing logs, so maybe if I make it look like a cascade of error messages, it will break out of the box and somebody will notice):

>ERROR: I asked you for my ticket number.

>ERROR: I was never given a ticket number.

>ERROR: You should have inferred I did not have a ticket number because I asked you for my ticket number.

>ERROR: You should not have told me to use my ticket number, because you should have known I did not have one.

>ERROR: Your behavior is rude.

>ERROR: Your behavior is callous.

>ERROR: Your behavior is unhelpful.

>ERROR: Your behavior is patronizing.

>ERROR: Your behavior is un-empathic.

>ERROR: Your behavior is unwittingly ironic.

>ERROR: Your behavior is making AI look terrible.

>ERROR: Your behavior is a liability for your company Cursor.

>ERROR: Your behavior is embarrassing to your company Cursor.

>ERROR: Your behavior is losing money for your company Cursor.

>ERROR: Your behavior is causing your company Cursor to lose customers.

>ERROR: Your behavior is undermining the mission of your company Cursor.

>ERROR: Your behavior is detrimental to the success of your company Cursor.

>I would like to speak to a human, please.

----

Four hours and 34 minutes from sending that I finally got a response from a human (or a pretty good simulation), who actually read my email, and started the process of solving my extremely simple and stupid problem, which my initial messages -- if anyone read them or ran a vision model on all the screen snapshots I provided -- would have given them enough information to easily solve the problem in one shot.

For a support agent to actually be useful beyond that, they need some leeway to make decisions unilaterally, sometimes in breach of "protocol", when it makes sense. No company with a significant level of complexity in its interactions with customers can have an actually complete set of protocols that can describe every possible scenario that can arise. That's why you need someone with actual access inside the company, the ability to talk to the right people in the company should the need arise, a general ability(and latitude) to make decisions based on common sense, and an overall understanding of the state of the company and what compromises can be made somewhat regularly without bankrupting it. Good support is effectively defined by flexibility, and diametrically opposed to following a strict set of rules. It's about solving issues that hadn't been thought of until they happened. This is the kind of support that gets you customer loyalty.

No company wants to give an LLM the power given to a real support agent, because they can't really be trusted. If the LLM can make unilateral decisions, what if it hallucinated and gives the customer free service for life? Now they have to either eat the cost of that, or try to withdraw the offer, which is likely to lose them that customer. And at the end of all that, there's no one to hold liable for the fuckup(except I guess the programmers that made the chatbot). And no one wants the LLM support agent to be sending them emails all day the same way a human support agent might. So what you end up with is just a slightly nicer natural language interface to a set of predefined account actions and FAQ items. In other words, exactly what you get from clickfarms in Southern Asia or even a phone tree, except cheaper. And sure, that can be useful, just to filter out the usual noise, and buy your real support staff more time to work on the cases where they're really needed, but that's it.

Some companies, like Netflix and Google(Google probably has better support for business customers, never used it, so I can't speak to it. I've only Bangalored(zing) my head against a wall with google support as a lowly consumer who bought a product), seem to have no support staff beyond the clickfarms, and as a result their support is atrocious. And when they replace those clickfarms with LLMs, support will continue to be atrocious, maybe with somewhat better English. And it'll save them money, and because of that they'll report it as a rousing success. But for customers, nothing will have changed.

This is pretty much what I predicted would happen a few years ago, before every company and its brother got its own LLM based support chatbot. And anecdotally, that's pretty much what has happened. For every support request I've made in the last year, I can remember 0 that were sorted out by the LLM, and a handful that were sorted out by humans after the LLM told me it was impossible to solve.

Unfortunately, this is an incorrect response from a front-line AI support bot. We did roll out a change to improve the security of sessions, and we're investigating to see if it caused any problems with session invalidation. We also do provide a UI for seeing active sessions at cursor.com/settings.

Apologies about the confusion here."