Hacker Newsnew | past | comments | ask | show | jobs | submit | jmarbach's commentslogin

Anchor Browser has documentation here showing how to combine x402 with an agentic browser session.

https://anchorbrowser.io/blog/pay-to-win-coinbase-x402-ancho...

We are not far off from humans giving a monthly allowance to their agentic counterparts.


As long as the agentic browser can automate my PirateBay tasks, I don't intend to overcomplicate it with payments and such.


Awesome product! Although Trigger.dev is fully capable, if you want to skip installing the browser infra and offload it to a remote session, I wrote a tutorial recently on how to use Anchor Browser with Trigger.dev to achieve this: - https://trigger.dev/docs/guides/example-projects/anchor-brow... - https://anchorbrowser.io/blog/integrate-trigger-dev-and-anch...

Looking forward to tracking Trigger.dev's success in the future.


I recently ran a test on the page load reliability of Browserbase and I was shocked to see how unreliable it was for a standard set of websites - the top 100 websites in the US by traffic according to SimilarWeb. 29% of page load requests failed. Without an open standard for agent identification, it will always be a cat and mouse game to trap agents, and many agents will predictably fail simple tasks.

https://anchorbrowser.io/blog/page-load-reliability-on-the-t...

Here's to working together to develop a new protocol that works for agents and website owners alike.


There's a term for this: an inconvenient truth.

Cheap and abundant energy is strongly correlated with prosperity. Every barrel of oil produces roughly 1,700 kWh of thermal energy. In countries with low cost of oil production like Saudi Arabia and Iran, that means electricity generation for less than $0.01/kWh. The only viable technology to compete with oil and gas over the long term is Nuclear.


I was thinking the same. Wouldn’t it be better to let agents buy access to your site? It wasn’t feasible with the Google monopoly. Now with dozens of agents competing for info it seems feasible to put a tollbooth in front of your site.


doesn't that depend on the purpose of the visit? Is it not the choice of a publisher?


From The Bitcoin Standard:

"The reduction in the purchasing power of money is similar to a form of taxation... As people start spending more and saving less, they become more present oriented in all their decision making... this helps explain why civilizations prosper under a sound monetary system, but disintegrate when their monetary systems are debased."


Yes, we should return to the gold standard so that we can all buy snake oil like in the old days.


You're missing the point. I actually had this realization on my own and had heard that the concept was outlined in the book which is what prompted me to read it.

Cheap money cheapens everything, because the velocity of money is high and so capital turnover is the name of the game. To make a profit, what you sell has to be cheaper than the money you get. It cheapens people because they have to constantly be scratching for a buck just to keep up.


Yes, I agree with your point. It reminds me a little of the ongoing debate over CDN vs Edge. However, one difference we offer is that eventually our 'cache' will flush to a persistent storage layer - so you don't have to think about managing your memory or disk resources. Data not used for weeks ends up in low-cost object storage - further saving you from high-cost memory storage costs and the repetitive task of performing this archiving operation yourself.


> eventually our 'cache' will flush to a persistent storage layer

What happens if the server goes down before the flush?


When a blob is saved, first I write it to Postgres (https://neon.tech), so that ensures there's a persisting backup. However, it's typically a waste of money to store infrequently accessed blobs in disk with Postgres over months and years. After 4-6 weeks data is offloaded to object storage - so that you benefit from low long term storage costs.

The lifecycle of a blob works out roughly something like as follows, based on last read date:

< 30 mins ago

- In-Memory: Cloudflare CDN

< 30 days ago

- In-Disk: Redis Auto-Tiering Memory/Disk combination

- In-Disk: Postgres

> 30 days ago

- Object Storage: Backblaze B2


Cloudflare wrote a blog post about their bandwidth egress charges in different parts of the world: https://blog.cloudflare.com/the-relative-cost-of-bandwidth-a...

The original post also includes a link to a more recent Cloudflare blog post on AWS bandwidth charges: https://blog.cloudflare.com/aws-egregious-egress/


Thank you for creating this. I've been looking for something that provides a more lightweight alternative to LangChain.


Thank you for saying so! It’s very gratifying that I’m not the only one who finds this useful :)


The author is correct. Growth is typically just a debt-fueled spending binge. The cancer is actually the fiat, soft money that’s improperly aligning incentives in the economy.


> The cancer is actually the fiat, soft money that’s improperly aligning incentives in the economy.

What a conclusion. Debt and borrowing exist in hard money environments too. Debt is as old as time.

Low interest rates reduce the threshold for what could be considered a successful business from a macroeconomic perspective, though, and can lead to misallocation of capital. Nothing to do with fiat.


Debt-fuelled spending binges were just as common before fiat. In fact, booms and crashes were more frequent and severe because there could be no central bank to turn the heat down under the cookpot.


It's the other way round. Dept is discounted potential future growth.

Potential growth and the ability to pay back dept is the foundation for receiving money.

What the author ignores is that it is a race. There are many opportunities but not all will be successful. Failed investments transfer the money from those who made wrong predictions to those who made successful ones. This creates sustained progress because those who are good at predicting the future have the most influence.


Once you have a lot of influence you can influence the future instead of predicting it. This is a handy way to profit without providing any value to the rest of the system.


Like high frequency trading, it's also valuable because things that are important to those in power are protected.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: