Live data from Hacker News

Temporary Cloudflare accounts for AI agents

blog.cloudflare.com

121–130 of 173 posts

Re: Temporary Cloudflare accounts for AI agents

#121

Earlier quoted context omitted.

Interesting idea ... doesn't fit my style of content consumption, but it might fit yours. I went for a personal newsfeed, agent pulls news form ~100 feeds related to my interests. Then reads all articles for me and orders them by how interesting they might be for me. I specifically asked for vector embeddings, up/down votes (-2..+2), visited status, LLM content evaluation. Probably there are some other mechanisms I d…

So this actually runs within ollama, which you then leave up full-time? Or only when you manually want to refresh your news feed?

The prototype runs through ollama on my laptop while I browse. I usually have few hundreds stories ready from the previous session, as new stories come in they get processed in the background while I browse the old ones. It processes stories faster than I consume them.

When I move it to the server I might consider waking it up periodically to pull and analyze new stories and perhaps notify me if something absolutely great shows up.

There are so many possibilities for tuning it. And I don't need to think how to make it secure (beyond the basics), ultra performant, fitting other people's tastes and so on because this program has audience of one.

Re: Temporary Cloudflare accounts for AI agents

#123
post #47

Looks like Cloudflare still haven't shipped the most valuable possible feature for Cloudflare Workers though: hard billing caps. I want to set a cap of $100/month and know, for sure, that if something untoward happens my apps will all stop serving traffic rather than me getting hit with a bill for $1000s. The safest way to use Workers is on the free tier, which will shut off after 100,000 requests/day: https://develo…

I've dealt with this before. The problem with doing a billing cap is that now you are bringing an out-of-band batch system (billing) in-band. The only way to do a dollar cap is to constantly calculate your bill. Capping it at 100K requests is a lot easier, because it's a single number that can be incremented easily in a distributed way. It's the same reason it took AWS forever to offer billing caps, and even today, t…

I am very sure what you’re saying is not true. It’s a viable-looking technical excuse, but you can easily understand that it’s false.

Let’s make a thought experiment.

CEO of Cloudflare introduces hard billing caps at a _business_ (not technical) level. Your organization will never be billed more than the level you set. Your app may stop, or may continue running, but above the monthly cap it’s free for you, it becomes Cloudflare’s expense if they didn’t pause the services.

I guarantee you that in this case, all technical issues you’re talking about would be solved in three weeks, and your service would go down within 3 seconds after hitting the cap.

If CEO decision were that any over-usage above the cap is deducted from employee bonuses from the specific product division that didn’t stop spending in time — all technical challenges would be solved in 48 hours.

Currently, there are literally zero organizational incentives for CloudFlare to develop any usage caps

Re: Temporary Cloudflare accounts for AI agents

#124
post #25
post #24

Hot damn... > Any agent can now run wrangler deploy --temporary and deploy a Worker to Cloudflare. This temporary deployment stays live for 60 minutes, during which time you can claim the temporary account, making it permanently your own. If you don't, it expires on its own. Forget about agents, Cloudflare just provided free scratch deployments - ephemeral for 60 minutes - for anyone . This is going to be amazing for…

I just tried this out: % npx wrangler deploy --temporary wrangler 4.103.0 ──────────────────── You must accept Cloudflare's Terms of Service (https://www.cloudflare.com/terms/) and Privacy Policy (https://www.cloudflare.com/privacypolicy/) in order to continue. By typing "yes", you agree to these terms. Type "yes" to continue. … yes Solving proof-of-work challenge… Temporary account ready: Account: Educated Celery (c…

By making it require interactive input to accept TOS they've made most agents unable to use it, but the effort is cool!

Re: Temporary Cloudflare accounts for AI agents

#125
post #47

Looks like Cloudflare still haven't shipped the most valuable possible feature for Cloudflare Workers though: hard billing caps. I want to set a cap of $100/month and know, for sure, that if something untoward happens my apps will all stop serving traffic rather than me getting hit with a bill for $1000s. The safest way to use Workers is on the free tier, which will shut off after 100,000 requests/day: https://develo…

I've dealt with this before. The problem with doing a billing cap is that now you are bringing an out-of-band batch system (billing) in-band. The only way to do a dollar cap is to constantly calculate your bill. Capping it at 100K requests is a lot easier, because it's a single number that can be incremented easily in a distributed way. It's the same reason it took AWS forever to offer billing caps, and even today, t…

The cost of each request or token may have a fixed cost - you do not have to query the main billing system for such things.

Re: Temporary Cloudflare accounts for AI agents

#126
post #24

Hot damn... > Any agent can now run wrangler deploy --temporary and deploy a Worker to Cloudflare. This temporary deployment stays live for 60 minutes, during which time you can claim the temporary account, making it permanently your own. If you don't, it expires on its own. Forget about agents, Cloudflare just provided free scratch deployments - ephemeral for 60 minutes - for anyone . This is going to be amazing for…

This is gonna be amazing for phishing, like most of the features Cloudflare offers (free Turnstile for fresh accounts, CF tunnels, pages.dev, r2.dev).

Re: Temporary Cloudflare accounts for AI agents

#127

Earlier quoted context omitted.

I've dealt with this before. The problem with doing a billing cap is that now you are bringing an out-of-band batch system (billing) in-band. The only way to do a dollar cap is to constantly calculate your bill. Capping it at 100K requests is a lot easier, because it's a single number that can be incremented easily in a distributed way. It's the same reason it took AWS forever to offer billing caps, and even today, t…

I am very sure what you’re saying is not true. It’s a viable-looking technical excuse, but you can easily understand that it’s false. Let’s make a thought experiment. CEO of Cloudflare introduces hard billing caps at a _business_ (not technical) level. Your organization will never be billed more than the level you set. Your app may stop, or may continue running, but above the monthly cap it’s free for you, it becomes…

You're describing a way to get the technical people to do the work, but that was never the problem. If you want them to do it you just tell them to, and then they spend however many hours doing it, instead of doing something else.

All technical problems are like that. You throw labor hours and hardware at them and progress is made. The question is, how much does it take, and is it worth that much? Which in turn depends on how willing you are to patronize someone else if they don't.

Re: Temporary Cloudflare accounts for AI agents

#128

Earlier quoted context omitted.

I am very sure what you’re saying is not true. It’s a viable-looking technical excuse, but you can easily understand that it’s false. Let’s make a thought experiment. CEO of Cloudflare introduces hard billing caps at a _business_ (not technical) level. Your organization will never be billed more than the level you set. Your app may stop, or may continue running, but above the monthly cap it’s free for you, it becomes…

You're describing a way to get the technical people to do the work, but that was never the problem. If you want them to do it you just tell them to, and then they spend however many hours doing it, instead of doing something else. All technical problems are like that. You throw labor hours and hardware at them and progress is made. The question is, how much does it take, and is it worth that much? Which in turn depen…

That’s kinda my point. We don’t have usage caps not because they are technically hard or impossible to implement (they’re not). It’s because the leadership thinks (likely correctly) that implementing them would just hurt company’s bottom line.

Re: Temporary Cloudflare accounts for AI agents

#129
post #47

Looks like Cloudflare still haven't shipped the most valuable possible feature for Cloudflare Workers though: hard billing caps. I want to set a cap of $100/month and know, for sure, that if something untoward happens my apps will all stop serving traffic rather than me getting hit with a bill for $1000s. The safest way to use Workers is on the free tier, which will shut off after 100,000 requests/day: https://develo…

To be honest their service is so cheap, that it's extremely unlikely to get such an attack without costing the attacker an equally equivalent amount.

Also, if it's really a problem or you are estimating it'll certainly be a problem, do email alerts or a strict shutdown if xx requests are hitting your account. You can have a simple counter in a KV.

Re: Temporary Cloudflare accounts for AI agents

#130

If eastdakota/jgc are here. - simply expose containers to the world directly - without having to go via workers. - You have other amazing parts of the stack anyway (D1, durable objects, a great object store). These aren't considered "lockin". - workers is "lockin" - not similar enough to lambda/cloud functions and so becomes CF specific. Not having a simple container based compute piece has made me hesitate in taking…

I think you have it the other way around? D1, DO, KV are lockin. The worker is not lockin as it's just JavaScript/WASM and can run in a regular browser.
Post reply on HN