Hacker Newsnew | past | comments | ask | show | jobs | submit | appcustodian2's commentslogin

Just in case it didn't occur to you already, you can just build whatever coding agent you want. They're pretty simple

Not just that but it will probably break later and ruin everything

N model is basically just N-1 model with revised context window handling and more compute thrown at it


I would think that it is still capable of exploring the codebase and reading other related files like any other coding agent already does.


source on the 8096 tokens number? i'm vaguely aware that some previous models attended more to the beginning and end of conversations which doesn't seem to fit a simple contiguous "attention window" within the greater context but would love to know more


well 8096 is just the first number that came to my mind, obviously frontier models have 32k or above, but they essentially they have a layer which "looks" at a limited view of the entire context window. {[1m x 3-4 weights] attention layer to determine what is actually important} -> {all other layers}


You think people open sourced things mostly because of license obligations?


how do you know when a page is "settled"?


Good question! ABP keeps a list of all same/parent/sibling network request and wait for them to complete within a timeout. If the timeout hits, it'll still freeze and screenshot back to the agent. There's a browser_wait() that the agent can call with increased timeouts to wait for network requests + DOM changes.


load event or "DOMContentLoaded" event. No?


those are factored into the wait heuristic only if there's a navigation event since clicks on an already loaded page won't trigger those. You can point Claude/codex at https://github.com/theredsix/agent-browser-protocol/tree/dev... and have it walk you through the wait heuristic step by step.


Don't worry we'll all be taking the Claude certification courses soon enough


How do you figure anything out? You go use it, a lot.


It's extremely fair to compare depreciation against MSRP. What's not fair is to say that they were being "sold new at massive discounts" when in reality it's an asterisk-ridden rebate process that applied to one model year under specific circumstances. That article was spam when it was written, can you provide a first party source for these massive discounts?


Depreciation is measured against the price someone actually paid.

The MSRP doesn’t matter. The S stands for suggested.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: