itissid

I think de-googling is itself has its costs. I've been waiting for a better solution to email. On a related note fundamentally I think the incentives to keep email infra alive is linked to the same incentive rooted in the core belief held by companies/services that ads work.

If there was an inflection point to break that perception — like covid gave a pause for thought for location based ad targeting — and hence the incentive, perhaps we can kick email as one of the ideas whose time has come.

I am rooting for ATproto to be the replacement.

In any case running an agent framework in anything but a strict environment like openshell or a VM with a non rooted container and with a firewall out side of that containment is the definition of stupidity.

I am ratting this out to the Tree Beard

So if you want to judge as a customer for selection and figure out how likely a new(ish) PaaS company going to get breached, how would you evaluate them?

1. Ask them about what percentage of their own resources goes towards cybersecurity, audits etc. Would they even tell you.

2. Technical stack maturity. If the details are available, because they won't reveal any of it to you.

3. Other signals: Do they give talks on platform security, who is incharge of their cyber security.

How is that ever going to work out? The speed of discovery for LLMs is so fast, these places are getting breached more often than not due to a human errors. Its really hard for machines, let alone humans, to guard against a lot of LLMs going against them 24x7.

Has someone read this and Pearls in Graph Theory and can tell me which one they liked more as an intro? I found the former a lot of fun and was a good introduction for high school math grade. I saw a few problems and they looked just a bit beyond, but not by much! A bit of probability theory is well within e.g. Exercise 3 in the "The “cop-and-highway-robber game” asks the probability of a robber getting caught were they to choose an edge to rob and one of the vertices of that edge was chosen by a cop. Fun.

It's latent but not like impossible to comprehend latent. No?

if I understand taking LLMs as an example certain neurons will fire based on certain motifs, then one can change the phrases or sentences around that motif and _predict_ if the same neurons would fire.

Like if I said "I like cars, but I like rockets better. Can you suggest some rocket models to fly?" and Neuron X fired every time it saw a `, but` and attended to what followed it, that would give you a good way to _understand_ when it changed and what might have caused it.

My understanding is that this is now clearly visible behavior.

Ive read 1/3rd of it. It's long and I will read most of it. But This is good news from a safety perspective no?

If its grouping circuits based on motifs and when they fire — and it applies to large networks — then one should be able to literally query or debug a reconstructed database and check against actual activations. More importantly If this was a hand-wavy thing to do earlier for safety, it's not anymore because it's on more solid ground using Normal Science.

> So why would you lock yourself in...

Many people don't even know what locking in means. The crowd in this forum < 1% of the world do, you and I do, and maybe a few outside. There are only laymen outside of 99%. No one i know of knows or uses a harness. They don't know the large number of VMs built on say Hermes. They really don't care or have time. If you give them a ready made product thats a click away, and its good enough, they will use it.

How paranoid should one be of, say for example, a wasm vulnerability exploited on zero day by a bad JS ad?

I am scared for my parents to get exposed to this kind of thing from bad ad network actors. Does anyone have some practical concrete recommendations they took? Like I don't think they can install ublock origin and whitelist sites on demand in Firefox they way I do.

The only practical thing right now is to make sure they don't have the money on device and have 2 fac for email and bank accounts. But every now and then there are phishing attamepts that they could fall prey to.

I think a lot of people in this thread are openly dismissive: "oh its just open claw, anyone can and many have build that".

I think what they are missing is the fact that there are not that many teams in the world that can deploy muse like product to A/B test a lot of hypothesis at the scale meta can at scale. I mean even if you could get to scale with DC you need a reason for people to use your product.

My mom and dad and their family have never heard of Claude and don't use chat gpt except once in a while as a search engine. But meta will figure out a way to insert this into modals and feeds to make people stumble and stick on it.

I am no meta fan, but I think people underestimate how fast product uptake there is for non Dev harness.