Also fix for free with v0 is not actually fix for free?

Absolutely 100% I’m noticing this. Specifically after topping up credits also.

It will build a metaphorical space ship with 1 prompt. Then if you tell it to change the color, it will take 50 prompts and break everything in the process. It very much feels like sabotage and it’s infuriating me. It got specifically bad 2-3 days ago.

@fernandorojo Explain yourself. This is getting more obvious every prompt.

@anshumanb @jacobparis @mleiter @fernandorojo You have 24hr to stop hiding out and address this, or I start posting video proof on social channels. Explain yourselves NOW!

This is because v0 pretty much revamps everything on every prompt

Hi @cappynate, I understand you are unhappy with your v0 experience.

For small changes like color or font, we recommend using the Design mode, which gives you better control over the styles and doesn't cost any tokens either.

However, making theories that v0 is "sabotaging" your project or threatening staff/community isn't an actual constructive feedback. Our team is working harder everyday to make it a better product but at the end it's AI and its outcomes are probabilistic, which can sometimes be less than ideal.

You can overcome this by using custom instructions, design mode, and prompt enhancements. Here are some resources you can use:

• https://community.vercel.com/t/custom-instructions-in-v0/16782

Vercel Community

Custom instructions in v0

In v0 there are three places where you can add custom instructions that are added to your messages Using these well will guide v0 into producing better code...

• https://community.vercel.com/t/best-practices-suggestions-for-knowledge-instructions/21948
• https://community.vercel.com/t/underrated-feature-in-v0-chatbox-enhance-prompt/22609

Don’t gaslight me.

The model works wonders when my account is nearing empty. Then when my account is funded, it breaks basic stuff. Predictably, like clockwork. Literally single item changes (change 1 single color code, reduce a margin). It ignores detailed instructions, it ignores verbatim instructions, it amends code that is copied verbatim. I didn’t start this thread, so clearly I’m not the only one experiencing this.

I appreciate the design mode suggestion and will try it. Looks helpful, thank you.

However:

-V0 has stuck in a retry loop for 9.5min bleeding tokens, all for a single line change. -V0 repeatedly creates syntax errors on simple single line changes. (Seemingly intentionally) -V0 charges me for “Fix Free” edits repeatedly. -Recently (last 2-3 days), V0 started overweighting old messages vs the most recent one.

I’m giving you the feedback. Please show a willingness to do something with it.

Thanks for sharing the individual issues.

Could you share the last message id where

• went into the retry look for more than a few minutes. 9.5 min sounds like a lot.
• any example of this would be helpful as well
• v0 charged you for the "Fix free"
• I will ask the team about what changes they did in last few days, they might be looking for this feedback.

I really appreciate you pointing these out. Would love to share these with the team and run a feedback loop once we have the message and chat IDs so they can inspect.

1. I’m not sure where to find the reference ID of each message, if you could direct me, that would help. Maybe these are them? Here’s screenshots in the meantime. Happened twice and tried other times before I cut it short. This was to move a back button from a header to a banner. Single prompt. The last one was changing colors.

   0B5jCRZmXME#q9e2R0p4UnnxTtfevsgH9sD1haI7IIMN 0B5jCRZmXME#GqqXDWeyN71sI2C0sihfsrwQORBmSajp

   

   

   

2. Here’s a string of 13 repeated Syntax or JSX errors on a simple, single page, wireframe app. From scratch, nothing complicated, only 250 lines of code. No functions, just mockups. As easy as it gets. This chat is right after I topped my account balance up. Here were the prompt summary that generated each Syntax/JSX, most where I explicitly warned it not to touch structure. Again this started right after the largest account top-up I’ve ever made.

   Again, I don’t know how to link them, but here’s this: https://v0.app/chat/profile-page-real-text-80-compl-qOAuUqUjMRG#9l4btjZxdtzF44qY9uzOFdPU4LwPucVz

   V15 - Change avatar Z axis v18 - Move + style single button V22 - Change serif font V25 - Move more button V26 - Subtle button and text styling V28 - Shuffle 3 components V35 - Align button to another V37 - Reskin theme, colors only (3m33s) V39 - Retry reskin, colors only V40 - JSX error from color changing V41 - JSX error (3m36s) V43 - Retry reskin, explicitly colors only. V44 - Exasperation. (7m5s)

3. V0 Charging for “Free Fixes”, I’ll need to get a video. But I’ve visually watched it nearly every time (say at least 60%) it charges me.

   That should be enough to keep you busy for now.

As the Op, I do think CappyNate might have taken this a bit far BUT he did get your attention. Gaslighting us for asking if others are feeling the same is not appropriate. I personally love what you fine people have made but the experience we’re reporting is REAL.

v0 charges me EVERY time I click fix for Free with v0. The initial thought may be free, probably not, but then every follow up, not a new message just it figuring itself out, is for sure charging even though it’s part of the same “Fix for Free” series of thoughts. I left it thinking the other night and came back to ~6.00 credits disappearing AND the problem wasn’t fixed and I had to restore and re-prompt.

I’ve started just walking away when I can tell it’ having a spell and coming back later. I’ve spent and plan on continuing to spend a fair amount of money with you but this gets rather frustrating at times…. like personal hell level frustrating.

I also struggle with V0 charging me for “Free FIxes” its not all the time but when errors do occur at times its 50/50 if v0 charges you or not I have made a thread about it and no response.

Hi @cappynate, I think you got the message Ids correct. I'll still share the step below for anyone else looking to share:

2. I see. The timing of these issues definitely makes it look weird. Let me direct your messages to our Support team and product team.

3. For the "free fixes" can you check the message billing history and see if the free fixes were not reimbursed? I need to confirm this one with the team.

Thanks for sharing your points here @corebytes and @ben-6576. Please add your message and credits consumption information like CappyNote so I can investigate further.

That’s good feedback, Eric. We saw some abuse of the free fixes when we launched it so have a limit on the number of times fix with v0 is free each day (99% of our users never hit that limit).

That said, the UI is not clear about when you’re past that limit and Fix with v0 is no longer free. We are fixing that shortly!

See my message to Eric – there’s a fraud/abuse limit on the number of times each day that Fix with v0 is free. We’re updating the UI shortly to better reflect that.

My team (v0) cares deeply about improving the performance of the agent. If you have feedback or examples where it fails to fix issues or gets stuck in these negative loops, please share them with us (here or via the feedback widgit in the app) – we will dig in and find ways to optimize.

The error message shows entirely red without dialogue or the fix for free button

So yesterday I noticed that my fixes were no longer free, and I saw it commended in the forums that there’s new logic to avoid abuse.

I don’t disagree with the logic to add abuse prevention measures, but a daily limit is a really bad approach IMO as it doesn’t count for the overall spend of a user - I was using V0 simultaneously over two projects yesterday meaning I was spending a lot, but also there were errors. I ran out of free fixes by lunchtime and it stalled work as I’m not going back to paying to fix things that should be correct.

You should rework this taking into account not just the volume of prompts, but historic prompt usage/spend on a rolling basis (last 30d or something)

I’m sure that many users likely have days where they don’t have issues, until they do where then there’s quite a lot of issues all on one go, a hard daily limit does not help with this.

Often I see a Fix with V0 where I’m pretty sure I know what the issue is, and with a little bit of context (like context about the DB logic) stuff could be fixed with lower token usage, and less repeated efforts to fix.

Naturally this would open up an abuse mechanism where people could stuff additional request to get them as part of free fixes, so logic could be for AI to split the requests:

1. Fix + Fix context

2. Additional request

   I think implementing something like this would help to move things along well for users

Hey, @alexhandsaker-7128! I moved your two topics into this discussion as it's both relevant.

The v0 team are already on this thread reading through it, appreciate you taking the time to share your feedback.

Here’s another example of this whole comingled issue: Eating credits, Charging for fixes, Looping, Running rogue 7 minutes, Questionable stuff, etc.

This attachment is a single prompt. It’s even heavily shortened.

-V0 worked on a task and created a syntax error, (credits charged obv). -It then automatically tried to fix that error unsuccessfully (credits charged here too). -It continued automatically retrying, creating a new syntax error (when “fix free with V0” showed). -It did this for 7 minutes, draining my account. -I did 3 prompts, it did this on each one. -In total it charged me $5, and still submitted a broken version with syntax errors.

All times it tried automatically “fixing”, the “Fix Free with V0” banner showed on the screen to do a manual fixing. But the system was stuck in prompt/working/retrying, so I couldn’t click it.

From a usability standpoint, auto-fix is great. Set-it and forget it.

But not if the result is bad, it runs rogue for 7min+, and charges for every fix when it says it won’t. I feel like I have to watch it like a hawk to prevent runaway and draining my account. It just leaves a really bad taste in my mouth.

Chat links: (7min): https://v0.app/chat/nostr-post-cards-5S4qQ0dvtdn#ZORrqZK4SbYXrfHwyqhrlvrJySneg3f3 (5min): https://v0.app/chat/nostr-post-cards-5S4qQ0dvtdn#zLRAGjccKL46MWrg2rL0oicZ8tpE2wMY (5min): https://v0.app/chat/nostr-post-cards-5S4qQ0dvtdn#9qmAz6qoPdjhjUQfkQBuJhpvbAU3lJHW

I noticed this same issue. I saw that i had 1 more message available. After the previous message (when it went from 2→1) there was a small bug. I saw the button where it said it was free, where the error was an invalid code issue from the previous change. I clicked the button (having 1 more message before clicking), and immediately the number of messages dropped to 0 and i got the popup about needing to subscribe. This is the second click of that button for me today, so I’m pretty sure i lost 2 of my free messages for the day.

I agree this is something that should be added, but I spend quite a few credits every day and do encounter quite a bit of errors. All my fixes should be free nonetheless of amount of errors v0 makes as that it not my fault! I would appreciate fixing this issue rather than any refund, as long term this will cost me hundreds. If i am hitting the free fix limit then that is simply poor quality on v0!

Ya, how do you abuse v0 messing up?? It messed up and the fix with v0 button is to fix a mess up that it acknowledged it caused. I imagine that’s why you rolled out fix for free in the first place… the reasoning of “abuse” sounds very… very fake.

it’s an amazing tool, please fix it.

The part that is confusing is does free mean it costs 0 messages and doesn’t charge credits or that it costs 1 message and doesn’t charge credits. What does “free” mean? Shouldn’t it be very clear what is going to happen when you click the button?

Exactly. How do you “abuse” free fixes?

Manually editing code to create an error while slipping another request in? I can’t see it exactly. Regardless, close that hole instead of gouging. Again, I’m more concerned V0 is intentionally creating errors to gouge me, not the other way around. It threw less dumb errors yesterday, but is back to incredibly dumb stuff today again.

I can confirm I have seen people posting about doing this in various discords. I am unsure of the exact process but I believe original implementation uses general error loggging with a certain tag, I have seen it in code with [V0] somehow people keyed in on that.

I have experienced these issues often (charging for fixes and long working times). Not a big deal to me, I understand what we are dealing with and v0’s capability on most things is insane and well worth it.

That being said I have mitigated most of them doing the following in no relevant order:

1. Clearing context by duplicating the project. (Would be cool to have /clear-context like bolt)
2. Adding instructions around troubleshooting and referencing online docs and enabling them.
3. Switching planning mode on and off.
4. Changing models and asking to review previous work and create plan.

One of these fix it 95% of the time and I am doing heavy stuff e.g. AI SDK, UI SDK, Chatkit etc.

I am still getting this issue any updates? @pawlean

As soon as my free $2 credits hit tonight, V0 works flawless. Perfect track record.

The instant the free credit runs out and goes back to paid credits V0 goes back to playing absolutely stupid.

V0 drains my entire account ignoring directions on a single, simple task, over the course of 30 prompts. This is BS guys. This pattern is too reliable to be anything other than sabotage by Vercel. I feel I am being scammed. Shall I just run free credits and not pay?

I came here specifically for this. Is the team planning to refund all the credits we’ve had to use just to fix projects? Things as simple as adding text or changing a logo?

I’ve already spent 60% of my top-up credits just trying to restore the website to its previous state after v0 mistakenly deleted or severely damaged it because of a simple edit. When we’re using free credits, you get a pass. But when you start charging people to use it, issues like these are unacceptable.

Same issue here, no reaction to any prompt with fix in the beginning. Dont like it. it charged me quite a bit.

For full transparency, the original title of this thread was “Is V0 Sabotaging Responses” (or something to that effect).

The title was changed by Vercel team to “Is Fix with V0 Free?” to cover up any questions about sabotage by Vercel. OP @ben-6576 can comment on the exact title he used, but it was not solely related to V0 Fixes Being Free. I’m still asking questions about sabotage. Because it feels intentional and patterned. And changing the title of this thread does not help Vercel’s case at all.

If, as a business, you are running compute losses due the $2 daily credits you offer, I completely understand this issue. But if your response to recoup those losses is to gouge paying customers by throwing fake errors to run our accounts down, that’s a big problem. The solution is to just get scrap/reduce the daily $2 credits. I have proof of nothing. These are merely the patterns I observe with my own eyes and usage.

We are giving you the benefit of the doubt by keeping these convos in relatively obscure channels here. Mostly out of public light. That will change without viable explanations, service corrections (refunds), or remedies.

I thought that was strange. I actually thought I was getting notices on a related topic and didn’t realize they changed the name. That is quite troubling. I was simply asking the question if anyone else felt that way because it had gotten incredibly bad. Bad enough for me to stop everything I was working on and come and invest the time to post here to see if I was alone in my experience… and I can see the answer is a clear, “yes” many others are experiencing the same thing.

It’s an amazing product I see the potential but seriously, don’t try to cover up what you’re users are telling you their experience is. I burned 30.00 credits yesterday just trying to get it to stop breaking my blog page every time it changed a picture on a post. Only managed to “fix” it when I was @ 1.40 ish credits left. The pattern of that seems very weird and has been repeating quite consistently.

Hey @cappynate @ben-6576! Pauline from the Vercel team here

For full transparency: I updated the title of this thread to help consolidate everyone’s feedback into one place, since “fix with v0” has come up quite a bit. This helps us track feedback more effectively and makes it easier for new users to find and contribute to the ongoing discussion. It also helps us +1 this internally. It wasn’t meant to change the narrative in any way.

That said, I should’ve let you know before making the change; totally my mistake there, and I appreciate you calling it out.

We’ve already shared this feedback with the v0 team to help improve things moving forward. If you’d like to request a refund, you can raise a case at vercel.com/help 🙏

Regarding the patterns you’re seeing with credits, we’re not instructing the AI to burn through free credits or behave differently once you’ve paid. That’s simply not something we do.

I'd be happy to jump on a call with you @cappynate @ben-6576 if you want to show me the patterns you're seeing. Let me know and I'll DM you my calendar link.

Otherwise, feel free to share videos or screenshots or unlisted chat links with us so we can deep on what the issue could be. It would also help to share prompt examples!

Hi @pawlean, I can’t figure out who is going to reply to my message or just skip it, for many days I haven’t seen a response, I haven’t seen a hello, we’re also changing the topics, it’s all strange, of course, the service is top-notch or it seemed to me

I cannot share prompt examples here, because they contain a degree of profanities that you didn’t know possible.

But I can share this prompt link: Language. Forewarned: https://v0.app/chat/nostr-profile-overlay-nav-5rYhlx5TG3k#GPmS0Lsh7apeRzU7vPk1efQ3ZXAorN4f

This example contains 4 prompts in a row that V0 ignored my instructions. Very simple instructions: “remove click-away and swipe to close logic on a modal”. It ignored 4 times, in a row, for a total work time over 10mins.

2:25 2:37 3:01 2:22

I don’t know how much it cost me, but at least a few bucks. To make it worse. This was a sub-set debug attempt of a smaller very simple issue “overlay won’t scroll on phone”, which I’ve spent ~50 prompts, an entire day, close to $20 (fees per prompt seem to keep increasing), and is still unsolved.

Yet in a fresh testbed, it created an entire function, working, without bugs, in about 15 prompts, for maybe $1.50, with perfect functionality. Not just a single error, a whole function. This is beyond simple bug chasing (which I’m no stranger too).

Why am I paying for V0 to flat out ignore my instructions, 4 times in a row? Why does every prompt result in higher costs but lower output value? (feels bait and switch) Why can it write an entire app from fresh, for a $0.20, but changing a single integer can cost close $1?

I feel scared to even prompt it, because it will just take my money and dig a deeper hole. Now I’m $100’s of dollars into a project I feel I have to scrap. I feel completely ripped off, no other way to put it.

Here’s my, non profanity laced chat. because I’m staring at it go. It’s pretty clear that it identifies exactly what the problem is and then works… doing something.. and doesn’t fix or goes off on a hallucination and completely redesigns things. Which then I have to restore and try again.

I even updated the project rules with clear positive rules and affirmations. LOL, if that doesn’t tell you the level of personal hell I’ve seen I don’t know what else will.

Here’s another it just did right now. Even a PG-13 chat.

So to summarize. It fixed a decently complex flow issue in the first prompt, then mixed up logic on two buttons (back vs home). All it had to do was swap logic as clearly stated. Very simple. Like 5x easier than what it did in prompt 1. Instead, it flat out ignored me 3x on this simple task. It insisted it was correct, when I’m literally testing it and telling it the logic is flipped. It continues to triple down instead of taking the prompt to recheck its work. Then tries to confuse itself and me, to take us deeper astray. Just flat out playing dumb, throwing a bone, stringing along, burning credits.

Then finally after reverting, it swaps the logic correctly, fixing it by accident (still thinking it was correct but that my requirement changed).

Guess what time this correct final prompt was?

The same minute the free $2 daily credits hit the account.

The link you shared is private btw, so I can't see any of it. You can change the settings by clicking on Share > Visibility (Unlisted):

Thanks so much for sharing your feedback! This all really helps. I’ll pass it along to the team as we keep working to make the product better. We’re still early in the AI journey, so it’s natural for it to make mistakes.

Which screenshot is this?

In the meantime, feel free to get a refund on credits at vercel.com/help.

Your message was generated by AI and our spam bot flagged it as spam, that's why it was hidden. I recommend you write your messages without AI to prevent this from happening in the future.

I recommend you request a refund of credits over at vercel.com/help.

The string of screenshots above was right before daily $2 hit acct. Last one was right as $2 hit acct.

My hypothesis on this is WRONG though. Because on further testing V0 didn’t fix the issue, and went back to cyclical silly errors on the $2 credits. So it was just being bad on free or paid. No discrimination

I did this. Thank you. It was very easy. I requested an amount roughly equal to the bad performance (ignored prompts, spun tires, etc). I do thank you for this. It helps. Because bleeding money fighting the bot is exhausting and defeating. I get that it’s early still too.

If there’s 1 overall theme I can imprint on the frustration point as a user, it’s how V0 moves mountains on a fresh project. It’s fast, accurate, and will write almost an entire app with a single prompt. Then as the project progresses, I feel I have to shrink requests to line by line to wrangle it under control. Even that can take 5, 10, 20, even 50+ prompts to change a single thing. And not even a complex bug. Overall it just kills the cadence of the project over time. And these aren’t even complex codebases. Maybe 5,000 lines and effectively 4 pages, on a single device. All front end too.

If it could maintain the quality of the first 50-100 to even 200 prompts in a fresh project, all the way throughout a project, this would be the experience we want. And I’m not even sure it’s “context size” related either. Thank you for your patience with me regardless @pawlean .

Low credit v0 request seem to be more precise and accurate with their outputs. I just purchased credits and wasted the first $10 from the low quality outputs of the v0 agent, changing unnecessary things not requested. It changed the whole layout of a component without requested.

I think you implemented a noticeable “fix” … now the 2.00 daily credit is just as stupid as a topped up account. 👏🥳🙌

I guess it’s not too stupid if we keep feeding it money… 🤦‍♂️

I’ll be exploring options for the next project, I do hope you get your act together soon. This has so much potential.

I’m experiencing the same thing. First, it makes a mistake and then uses the credits to fix it. It doesn’t actually progress at all, since I’m using Premium.

Please see my response to you in the other thread / post.

There might be various factors behind this all. And again, sometimes these things happen. No AI tool agent will be perfect with a “fix for free”. So we have to learn to work with it, and ways to work around it, while the engineering teams continue to evolve the products.

Is this feature no longer available? Is this service no longer free?

I would also like to know the answer to this

I have gone through this even right now