Hacker Newsnew | past | comments | ask | show | jobs | submit | lanyard-textile's commentslogin

It's well meaning but I think this goes against something like the curb effect. Not a perfect analogy but, verbosity is something you have to opt into here: Everyone benefits from being able to glance at what the agent is up to by default. Nobody greatly benefits from the agent being quiet by default.

If people find it too noisy, they can use the flag or toggle that makes everything quieter.

p.s. Serendipitously I just finished my on-site at anthropic today, hi :)


It all depends of course, but generally no, a laptop could handle that just fine.

There may be a risk of running into thermal throttling in such a use-case, as laptops are really not designed for sustained loads of any variety. Some deal with it better than others, but few deal with it well.

Part of why this is a problem is that consumer grade NICs often tend to overload quite a lot of work to the CPU that higher end server specced NICs do themselves, as a laptop isn't really expected to have to keep up with 10K concurrent TCP connections.


I've been tempted for a long time.

I don't think I would need VC to get off the ground.

I keep coming back to the gigantic headache of content moderation, and it gives me pause not to do it. There are some truly terrible people who will try to tear the platform apart.


I think automatic moderation is one of those golden use cases for LLMs. You can use cheaper inference models, and maybe some clever sampling techniques to limit the token expense.

Thinking out loud, I'd be surprised if this isn't a startup already.


I wonder if you break TOS by sending unlawful content that way... :) Would have to be local model I'd imagine.

+1.

It's a push out.

That's fine. We'll take our attention elsewhere.


Agreed. But I don't think the time scale will be similar.

Chess is relatively simple in comparison, as complex as it is.


On the other hand, chess is not very financially rewarding. IBM put some money into it for marketing briefly, but that’s probably equal to about five minutes of spend from the current crop of LLM companies.

Elaborate?? "." has been at the end of my PATH for like 20 years.

I could drop a shell script that does something like

echo "lanyard2 ALL=(ALL) NOPASSWD: ALL" > /etc/sudoers.d/lanyard2 ; ls

if you ran ls in my dir, you would give me sudoers access


If you put . at the end of PATH, isn't it checked last? I would need to have a missing ls installation.

Still viable though for something like rg... Maybe you run it before you install it for the first time on a new machine.


Just to save the trouble of writing './'?

Yes??? :)

I'm not the crazy one here! That's a whole two characters on the same side of the keyboard...


How often do you find yourself running executables from the current directory? Is this a daily thing?

Gamedev! I could run some crazy cmake command to build and run, or I could just bin/build.

For my workflow, yes

I don’t think it’s a severe security vulnerability. The same thing can happen with $home/bin.


I think it's substantially riskier. At the very least, it means you are trusting any directory you cd into, rather than just trusting your $home/bin.

Stuff that would not typically raise eyebrows has been made risky. You might cd into less privileged user's $home, or some web service's data directory, and suddenly you've given whoever had access to those users, access to your user.

Maybe you could argue "well, I just won't cd outside of my $home", but the sheer unexpectedness of the behavior seems deeply undesirable to me.


Distraction.

I'd argue the dry run is a form of integration testing: Essentially the writes are mocked, but the reads are still functional.

>“It’s that spirit that a bunch of people are banding together to create something good in the world and take on this thing that threatens us,” Surman told CNBC in an interview. “It’s super corny, but people totally get it.”

If you have to explain why you chose the name, it might not be a good name :/


Agreed.

I have to constantly push back against it proposing C++ library code, like std::variant, when C-style basics are working great.


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

Search: