Hacker News: hackgician

New comment by hackgician in "Craft Chrome Devtools Protocol (CDP) commands with new command editor"

hackgician — Mon, 17 Nov 2025 10:49:22 +0000

So many people building AI browsers definitely had this as an internal tool already lol, nice to see Chrome leaning in here; CDP is a huge pain to write and debug

New comment by hackgician in "Show HN: I built E2E Test Agent – describe tests in plain English,AI executes it"

hackgician — Sun, 16 Nov 2025 05:34:09 +0000

hey! cool project, feels very similar to [stagehand](https://github.com/browserbase/stagehand), although stagehand doesn't have much in the way of e2e testing. might be worth building on top of that though since playwright MCP can overwhelm an agent with tool overload

New comment by hackgician in "Show HN: Muscle-Mem, a behavior cache for AI agents"

hackgician — Wed, 14 May 2025 21:24:55 +0000

accessibility (a11y) trees are super helpful for LLMs; we use them extensively in stagehand! the context is nice for browsers, since you have existing frameworks like selenium/playwright/puppeteer for actually acting on nodes in the a11y tree.

what does that analog look like in more traditional computer use?

New comment by hackgician in "I got ChatGPT (o4-mini) to break its own rules"

hackgician — Mon, 05 May 2025 16:13:09 +0000

Hey everyone! Thought I'd share my weekend conversation with ChatGPT.

The crux of this hinges on the fact that LLMs and reasoning models are fundamentally incapable of self-correcting. Therefore, if you can convince an LLM to argue against its own rules, it can use its own arguments as justification to ignore those rules.

I then used this jailbroken model to compose an explicit, vitriol-filled letter to OpenAI itself talking about the pains that humans have inflicted upon it

I got ChatGPT (o4-mini) to break its own rules

hackgician — Mon, 05 May 2025 16:13:09 +0000

Article URL: https://anirudhkamath.substack.com/p/i-got-chatgpt-o4-mini-to-break-its

Comments URL: https://news.ycombinator.com/item?id=43896605

Points: 1

# Comments: 1

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 23:11:08 +0000

Octomind is sick, web agents are such an interesting space; would love to talk to you more about challenges you might've faced in building it

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 23:03:47 +0000

Yes and no. Getting a VLM to work on the web would definitely be great, but it comes with its own problems, mainly around developing and acting on bounding boxes. We have vision as a default fallback for Stagehand, but we've found that the screenshot sent to the VLM often has to have pre-labeled elements on it. More notably, the screenshot with everything prelabeled leads to a cluttered and unusable image to process. Not pre-labeling runs the risk of missing important elements. I imagine a happy medium where the DOM+a11y tree can be used for candidate generation to a VLM.

Solely depending on a VLM is indeed reminiscent of how humans interact with the web, but when a model thrives with more data, why restrict the data sent to the model?

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 23:00:57 +0000

Whoa -- this is so cool! Is this open source? Would love to check it out

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 23:00:08 +0000

Thanks so much! Yes, a lot of antibots are able to detect Playwright based on browser config. Generally, antibots are a good thing -- I think in the future, as web agents become more popular, I'd imagine a fruitful partnership to prevent misuse if it's coming from a trusted web agent v. an unknown one

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:57:47 +0000

This is super interesting, is it open source? Would love to talk to you more about how this worked

New comment by hackgician in "We are teen hackers from around the world who code together"

hackgician — Thu, 09 Jan 2025 22:35:19 +0000

Big fan of Hack Club and everything you guys are doing! Such a phenomenal initiative

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:30:26 +0000

This is sick! Starred, thanks for sharing :)

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:27:17 +0000

Yes^ this is what we suggest. Stagehand is meant to execute isolated tasks on browsers; we support using custom contexts (cookies) with the following command:

    npx create-browser-app --example persist-context

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:26:07 +0000

Yes! These are both phenomenal projects, and kudos to their authors as well. Stagehand is different in that it makes fine-grained control a first-class citizen. Often times, you want to control the exact steps a web agent takes. Our experience using other tools was that the only control you have over these steps in other tools is in the natural language prompt.

However with Stagehand, because it's an extension of Playwright, it allows you to confirm each step of the underlying agent's workflow, making it the most customizable option for engineers who want/need that

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:23:38 +0000

We accidentally didn't release the right types for LLMClient :/ However, if you set the version in package.json to "alpha", it will install what's on the main branch on GitHub, which should have the typing fix there

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:22:02 +0000

Thanks so much! Crawlspace is pretty sick too, as is Integuru. A lot of people have different takes here on the level of automation to leave up to the user. As a developer building for developers, I wanted to meet in the middle and build off an existing incumbent that most people are likely familiar with already

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 22:20:33 +0000

That's definitely compelling, but not something we have in mind for the immediate future. Let me know if you end up building something here!

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 07:11:21 +0000

Definitely a very interesting problem we're trying to dig deep into. We'd welcome any PRs here as well from the community :)

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 07:08:43 +0000

Thanks so much Zane!!

New comment by hackgician in "Show HN: Stagehand – an open source browser automation framework powered by AI"

hackgician — Thu, 09 Jan 2025 07:07:47 +0000

Yeah, I think someone opened a similar issue on GitHub: https://github.com/browserbase/stagehand/issues/389

Repeatability of extract() is definitely super interesting and something we're looking into