> Stalwart Enterprise leverages AI technology to provide unparalleled email security and management. With AI-powered features, Stalwart Enterprise excels in accurately classifying spam, detecting sophisticated phishing attempts, and blocking various types of network attacks. This intelligent approach ensures that your email environment remains secure and reliable. Stalwart Enterprise comes equipped with a pre-trained large language model (LLM), offering robust out-of-the-box protection. Additionally, it supports integration with leading AI providers such as OpenAI, Anthropic, and other cutting-edge platforms, allowing you to enhance and customize your security measures. By utilizing AI, Stalwart Enterprise delivers a smarter, more efficient email solution that proactively safeguards your communications and data.
I've been unemployed for about 1 year now. I was in SF working in tech for about 7 years, and decided I don't want to do that anymore, so I quit.
It's been tough. The hardest part about being unemployed is it is very hard to structure your days because work is no longer the thing that is forcing you to get up, get out, go to bed on time, etc. It's also a strange feeling having to spend from your savings/emergency fund without money coming in, you feel bad and guilty for doing so, it's weird.
I'm changing careers. I've always liked teaching, so I'm doing volunteer english teaching while preparing to apply to go back to school in order to get a Masters in Education.
In the mean time, I'm also doing other small things. Learning about AI, going to board game meetups, doing some traveling, overall it's not the most fun part of my life, but I'm treating it as I will look back on this and realize this was necessary.
> The hardest part about being unemployed is it is very hard to structure your days
The irony is that it takes a lot more personal discipline to remain productive without any sort of feedback loop, but the unemployed are presumptively regarded as flawed and lazy :-)
I was in tech for over 20 years, and went from being good at my job/successful to being permanently disabled. My entire life was wired around providing for my family and supporting everyone around me both financially, and via my success.
I've lost that identity, and despite extensive therapy, meds, etc. I still haven't found myself yet.
I have that identity, ie being the pillar of stability and support for those around me.
One thing I worry about is getting a stroke or become blind, paralyzed or similar.
Having lost people around me or seen them fall seriously ill , made me realize things can change so quickly.
I admire ppl like yourself who keep going.
Or people like Paul De Gelder, who lost the majority of their limbs and then just keep going and seem to thrive.
I wonder how ppl like that change their mindset after such life events. What happens in the brain? Is it via therapy or effectively deciding to make the best with the cards you’ve been dealt.
From what you wrote, it sounds like you haven’t lost a core pillar of your identity, which is a positive mindset.
A friend at my coworking spot had a stroke a month ago. I was coming in on a monday morning and he was being carted off in the ambulance right as I got there. As in... door was open and his coffee and laptop were there, lunch in the fridge, and... I did't make the connection. I didn't see anyone being loaded in the ambulance, lights weren't on, etc. His family came by later to pick up his stuff.
He's been in an intensive care neuro unit for the past month. I visited about 10 days ago and he was having trouble talking, and... I suspect it might be long lasting or permanent.
We'd just spoken the Friday before, and had a meeting planned that morning. It all changed instantly, and there's no going back. It shook me up some, and I'm not affected at all, really, but seeing this happen to someone you know directly is... hard to take (for me anyway).
Here is a feature request. I want a Google chrome extension so that as I'm browsing the web, similar to how pocket used to work, I can bookmark a page to read more about it later.
Not super familiar with fly.io, but with a quick look at that page it should work just fine.
Just instead of dropping that camellia.conf to the WireGuard MacOS client or Linux wg-quick, spin up the TailGuard container somewhere (pretty much anywhere, but with good ping to fly.io). That way you should have the fly.io private network accessible in your Tailscale tailnet, it runs wg-quick internally alongside Tailscale anyway, just with a bit of scripting to automatically configure the network and the firewall to avoid connections leaking.
If it doesn't work, feel free to raise an issue and I can have a look.
My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind: https://brave.com/blog/comet-prompt-injection/.
This is a very valid concern. Here are some of our initial considerations:
1. Security of these agentic system is a hard and important problem to solve. We're indexing heavily on it, but it's definitely still early days and there is still a lot to figure out.
2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but it's a first step.
3. Our agents run in isolated browser sessions and, as per all software engineering, each session should be granted minimum access. Nothing more than strictly needed.
4. These attacks are starting to resemble social engineering attacks. There may be opportunities to shift some of the preventative approaches to the LLM world.
Thanks for asking this, we should probably share a write-up on this subject!
> 2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but it's a first step.
> [...]
> 4. These attacks are starting to resemble social engineering attacks. There may be opportunities to shift some of the preventative approaches to the LLM world.
With current tech, if you get to the point where these mitigations are the last line of defense, you've entered the zone of security theater. These browser agents simply cannot be trusted. The best assumption you can make is they will do a mixture of random actions and evil actions. Everything downstream of it must be hardened to withstand both random & evil actions, and I really think marketing material should be honest about this reality.
I agree, these mitigations alone can't be sufficient, but they are all necessary within a wider framework.
The only way to make this kind of agents safe is to work on every layer. Part of it is teaching the underlying model to see the dangers, part of it is building stronger critics, and part of it is hardening the systems they connect to. These aren’t alternatives, we need all of them.
Sure, but to clarify, so you are probably setting temperature to close to 0 in order to try to get as consistent output as possible based on the input? Have you made any changes to top k and/or top p that you have found makes agents output more consistent/deterministic?
This is a great post, thank you for sharing. I like the idea of giving hints to the LLMs.
To clarify, the example that was provided using `command_not_found_handler`, is that possible to implement in bash? Or perhaps you were saying this would be a nice to have if this functionality existed?
