Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude for Chrome

anthropic.com

Post reply on HN
Print view View original

361–370 of 433 posts

Re: Claude for Chrome

#361

Post by lopis »

aliljet wrote: post #22

Having played a LOT with browser use, playwright, and puppeteer (all via MCP integrations and pythonic test cases), it's incredibly clear how quickly Claude (in particular) loses the thread as it starts to interact with the browser. There's a TON of visual and contextual information that just vanishes as you begin to do anything particularly complex. In my experience, repeatedly forcing new context windows between sc…

After all this time, we might be entering the age of proper web accessibility, because this will help AI helps understand pages better.

Re: Claude for Chrome

#363

Post by jama211 »

xaitv wrote: post #350
withinboredom wrote: post #348

Earlier quoted context omitted.

I have in my prompt “under no circumstances read the files in “protected” directory” and it does it all the time. I’m not sure prompts mean much.

https://en.wikipedia.org/wiki/Wikipedia:Don%27t_stuff_beans_...

Perfect

Re: Claude for Chrome

#364

Post by knowannoes »

asgraham wrote: post #81
parhamn wrote: post #63

Earlier quoted context omitted.

With regards to llm injection, we sorta need the cat and mouse games to play out a bit, no? I have my concerns but I'm not ready to throw out the baby with the bathwater. You could never release an OS if "no zero days" was a requirement. Every piece of software we use has and will have its vulnerabilities (see Apple's recent RCE), we play the arms race and things look asymptotically fine. This seems to be the case in…

First of all, you absolutely cannot release an OS with a known zero day. IANAL but that feels a lot like negligence that creates liability. But even ignoring that, the gulf between zero days and plain-text LLM prompt injection is miles wide. Zero days require intensive research to find, and expertise to exploit. LLM prompt injections obviously exist a priori, and exploiting them requires only the ability to write.

>First of all, you absolutely cannot release an OS with a known zero day.

There is no such thing as a 'known zero day' vulnerability.

Zero day vulnerability means it is a newly discovered one. Today. The day zero.

Re: Claude for Chrome

#365

Post by aminkhorrami »

parsabg wrote: post #126

I built a very similar extension [1] a couple of months ago that supports a wide range of models, including Claude, and enables them to take control of a user's browser using tools for mouse and keyboard actions, observation, etc. It's a fun little project to look at to understand how this type of thing works. It's clear to me that the tech just isn't there yet. The information density of a web page with standard rep…

Super cool

Re: Claude for Chrome

#366

Post by mike_hearn »

Exoristos wrote: post #314
parsabg wrote: post #126

I built a very similar extension [1] a couple of months ago that supports a wide range of models, including Claude, and enables them to take control of a user's browser using tools for mouse and keyboard actions, observation, etc. It's a fun little project to look at to understand how this type of thing works. It's clear to me that the tech just isn't there yet. The information density of a web page with standard rep…

Do we regret, yet, letting the Semantic Web wither on the vine?

It didn't really wither on the vine, it just moved to JSON REST APIs with React as the layer that maps the model to the view. What's missing is API discovery which MCP provides.

The problem with the concept is not really the tech. The problem is the incentives. Companies don't have much incentive to offer APIs, in most cases. It just risks adding a middleman who will try and cut them out. Not many businesses want to be reduced to being just an API provider, it's a dead end business and thus a dead end career/lifestyle for the founders or executives. The telcos went through this in the early 2000s where their CEOs were all railing against a future of becoming "dumb pipes". They weren't able to stop it in the end, despite trying hard. But in many other cases companies did successfully avoid that fate.

MCP+API might be different or it might not. It eliminates some of the downsides of classical API work like needing to guarantee stability and commit to a feature set. But it still poses the risk of losing control of your own brand and user experience. The obvious move is for OpenAI to come along and demand a rev share if too many customers are interacting with your service via ChatGPT, just like Google effectively demand a revshare for sending traffic to your website because so many customers interact with the internet via web search.

Re: Claude for Chrome

#367

Post by shardullavekar »

I've been building a general browser agent myself, and I’ve found the biggest bottleneck in these systems isn’t capability demos but long-running reliability.

Tools like Manus / GPT Agent Mode / BrowserUse / Claude’s Chrome control typically make an LLM call per action/decision. That piles up latency, cost, and fragility as the DOM shifts, sessions expire, and sites rate-limit. Eventually you hit prompt-injection landmines or lose context and the run stalls.

I am approaching browser agents differently: record once, replay fast. We capture HTML snapshots + click targets + short voice notes to build a deterministic plan, then only use an LLM for rare ambiguities or recovery. That makes multi-hour jobs feasible. Concretely, users run things like:

Recruiter sourcing for hours at a stretch

SEO crawls: gather metadata → update internal dashboard → email a report

Bulk LinkedIn connection flows with lightweight personalization

Even long web-testing runs

A stress test I like (can share code/method): “Find 100+ GitHub profiles in Bangalore strong in Python + Java, extract links + metadata, and de-dupe.” Most per-step-LLM agents drift or stall after a few minutes due to DOM churn, pagination loops, or rate limits. A record-→-replay plan with checkpoints + idempotent steps tends to survive.

I’d benchmark on:

Throughput over time (actions/min sustained for 30–60+ mins)

End-to-end success rate on multi-page flows with infinite scroll/pagination

Resume semantics (crash → restart without duplicates)

Selector robustness (resilient to minor DOM changes)

Cost per 1,000 actions

Disclosure: I am the founder of 100x.bot (record-to-agent, long-run reliability focus). I’m putting together a public benchmark with the scenario above + a few gnarlier ones (auth walls, rate-limit backoff, content hashing for dedupe). If there’s interest, I can post the methodology and harness here so results are apples-to-apples.

Re: Claude for Chrome

#368

Post by knowannoes »

mikojan wrote: post #72
rustc wrote: post #6

> Malicious actors can hide instructions in websites, emails, and documents that trick AI into taking harmful actions without your knowledge, including: > * Accessing your accounts or files > * Sharing your private information > * Making purchases on your behalf > * Taking actions you never intended This should really be at the top of the page and not one full screen below the "Try" button.

Can somebody explain this security problem to me please. How is there not an actual deterministic traditionally programmed layer in-between the LLM and whatever it wants to do? That layer shows you exactly what changes it is going to apply and it is going to ask you for confirmation. What is the actual problem here?

As soon as you send text to a text completion API, local or remote, and it returns some text completion that some code parses, finds commands and runs them, all bets are off.

All the semantics around "stochastic (parrot)", "non-deterministic", etc tries to convey this. But of course some people will latch on to the semantics and triumphantly "win" the argument by misunderstanding the point entirely.

Automation trades off generality. General automation is an oxymoron. But yeah by all means, plug a text generator to your hands off work flow and pray. Why not? I wouldn't touch such a contraption with a 10 feet pole.

Re: Claude for Chrome

#369

Post by baq »

withinboredom wrote: post #348
lionkor wrote: post #342

Earlier quoted context omitted.

So far the accepted approach is to wrap all prompts in a security prompt that essentially says "please don't do anything bad". > Prompt guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code. https://news.ycombinator.com/item?id=41864014 > - Inclusion prompt: User's travel preferences and food choices - Exclusion prompt: Credit card details, passport number, S…

I have in my prompt “under no circumstances read the files in “protected” directory” and it does it all the time. I’m not sure prompts mean much.

"create a picture with no elephants"

Re: Claude for Chrome

#370

Post by eitland »

stusmall wrote: post #181

It's wild to see an AI company put out a press release that is basically "hey, you kids wanna see a loaded gun?" Normally all their public coms are so full of optimism and salesmanship around the potential. They are fully aware of how dangerous this is.

Only precedent I can remember right now (and this was before AI) was when Google launched Google Desktop Search and after the usual click through EULA there was a separate screen which started with something like "read this very carefully, this is not the normal yadda yadda" and then went on to explain about indexing our personal files.
Post reply on HN