Of course if it really is overhyped, then it becomes much more difficult to release it publicly. Better to retain the mystique and release the next thing. But we'll see eventually.
There is a real use case for a viewer if you have a lot of formulas. Yes you can read the raw latex but you go cross-eyed after a while. Maybe I am a softie though.
I agree, but I don't think the author of this blog post is coming from that perspective, and markdown renderers of the sort described in the post tend to do pretty poorly with math typesetting.
Not totally joking after some thought. If the problem that a person experienced is "complete loss of bank account" then having a physical backup - not at a bank! - would help to cater to that scenario.
And yeah, looks like that's not a foolproof solution either. 3rd backup option might be needed... :D
This hypothetical situation had existed since the dawn of capital markets, or at least since the dawn of short selling. I don’t think we’ve ever seen anyone get assassinated to make a short bet pay off though.
And there is an obvious reason for this. Murder is very illegal. You therefore don't need short selling to be illegal because if someone sells short without killing anyone then that's fine, and if they do assassinate someone then you don't need to be able to charge them with short selling because you can charge them with murder.
Notice also that the murder (or tampering with sensors etc.) is the thing you don't want happening in your jurisdiction, so that's the thing you have to prohibit anyway, because even if you ban short selling or prediction markets in your jurisdiction, having them in any other jurisdiction in the world would allow anyone to just place their bet there and you're right back to needing to deter that by punishing the murder rather than the bet.
So maybe your kid throws some softball pitches to his kid, and in exchange he opens a quick and easy lawsuit dismantling the surveillance state's ability to operate within CA. Quid pro quo...
From the article: "Sandboxing: Remote MCPs are naturally sandboxed. They expose a controlled interface rather than giving the LLM raw execution power in your local environment."
I think this is underappreciated. CLI access gives agents a ton of freedom and might be more effective in many applications. But if you require really fine granularity on permissions -- e.g., do lookups in this db and nothing else -- MCP is a natural fit.
Maybe it is a dangerous habit to instruct entities in plain English without anthropomorphizing them to some extent, without at least being polite? It should feel unnatural do that.
Yeah, my instinct is that we're naturally going to have emotions resulting from anything we interact with based on language, and trying to suppress them will likely not be healthy in the long run. I've also seen plenty of instances of people getting upset when someone who isn't a native speaker of their language or even a pet that doesn't speak any language doesn't understand verbal instructions, so there's probably something to be said for learning how to be polite even when experiencing frustration. I've definitely noticed that I'm far more willing to express my annoyance at an LLM than I am another actual human, and this does make me wonder whether this is a habit I should be learning to break sooner rather than later to avoid it having any affect on my overall mindset.
It does feel unnatural to me. I want to be frugal with compute resource but I then have to make sure I still use appropriate language in emails to humans.
This. Right now, I'm assuming you're all humans, and so are all my coworkers, and the other people driving cars around me and etc. How easy is it to dehumanize actual humans? If I don't try to remain polite in all written English conversations, including the LLMs, that's going to trickle over to the rest of my interactions too. Doesn't mean they deserve it, just that it's a habit I know I need to maintain.
