Some people would rather not hand over all of their ability to think to a single SaaS company that arbitrarily bans people, changes token limits, tweaks harnesses and prompts in ways that cause it to consume too many tokens, or too few to complete the task, etc.
I don't use any non-FLOSS dev tools; why would I suddenly pay for a subscription to a single SaaS provider with a proprietary client that acts in opaque and user hostile ways?
I think, we're seeing very clearly, the problem with the Cloud (as usual) is it locks you into a service that only functions when the Cloud provides it.
But further, seeing with Claude, your workflow, or backend or both, arn't going anywhere if you're building on local models. They don't suddenly become dumb; stop responding, claim censorship, etc. Things are non-determinant enough that exposing yourself to the business decisions of cloud providers is just a risk-reward nightmare.
So yeah, privacy, but also, knowing you don't have to constantly upgrade to another model forced by a provider when whatever you're doing is perfectly suitable, that's untolds amount of value. Imagine the early npm ecosystem, but driven now by AI model FOMO.
We do make Claude and Mistral available to our developers too. But, like you said, security. I, personally, do not understand how people in tech, put any amount of trust in businesses that are working in such a cutthroat and corrupt environment. But developers want to try new things and it is better to set up reasonable guardrails for when they want to use these thing by setting up a internal gateway and a set of reasonable policies.
And the other thing is that i want people to be able to experiment and get familiar with LLM's without being concerned about security, price or any other factor.
Anything a border official says is implicitly backed with the threat of, at a minimum, detention without trial and without basic humane treatment like access to drinking water. Heathrow has well publicised cases (and is not unusual in this).
It's probably much more boring. The choice was likely between leaving the whole water bottle and its contents in a bin of forbidden/discarded items, going home and missing the flight, or chugging it, or arranging a courier for said bottle.
Probably the act of defiance of pouring the contents onto the floor where there was no drain was implied to be disruptive and would have lead to harsher sanction for no reasonable payoff.
As suspected, your claim is grossly exaggerated. You have one blog post from a decade ago (which I remember reading at the time since I met the author at a conference) which is about being denied entry as the grounds for travel were misdeclared, and not about oppressive security theatre at the passenger screening area.
> which is about being denied entry as the grounds for travel were misdeclared
Yes but not really. It's mainly about the kind of treatment you face when you get on the wrong side of the airport machine, and as such it's exactly what you're implicitly threatened with if you step out of line.
Heathrow is a fucking miserable place with spiteful staff and it would not surprise me one bit if someone decided to fuck with a traveller this way. I saw a girl running to catch a bus to another terminal for a connecting flight, and the guy controller her made an enormous stink about her "breathing on me". She was polite and apologetic but she got pulled aside and made to wait for everyone else to get through, got sternly chastised before being allowed to continue (whereupon she missed the connecting bus and presumably her flight). Same trip I saw them them shouting and swearing at disabled travellers who needed wheelchairs. Every other member of staff in the airport was stood around fucking with their phones and seemed furious whenever they had to do their job.
Given that the border officer has discretion to refuse you entry, failing to down your drink can turn into attempting to enter illegally if they want it to.
Yes, it’s in the same space as Gibson’s GRC DNS Benchmark — that tool has been around for years and set the standard for GUI‑based testing. This project takes a different angle: it’s CLI‑first, scriptable, and adds modes for quick checks, deeper benchmarks, and ongoing monitoring. So it’s more aimed at automation and sysadmin workflows than interactive GUI use.
There are 'best to brush' timelines around eating/drinking. Usually you want to either:
- Brush no less than 15m before eating
- Do not brush until 45m+ after eating
I don't fully understand the science, as I'm not a dentist, but it's something related to the way that things stick to/are absorbed by enamel and dentin.
I believe water is the exception here, you can drink water and then immediately brush. You should not brush and then immediately drink water though. You want the toothpaste to stick around and form a barrier.
Supposedly, after eating the pH in the mouth drops and becomes more acidic, which softens the enamel, so brushing will do more harm than good. That's my understanding.
reply