Elevated errors across many models

https://www.theguardian.com/technology/2021/oct/05/facebook-...

I have a memory that Slack fell into this trap too (I could be wrong)

A tech company that publishes the postmortems when possible always get a +1 in my eyes, I think it's a sign of good company culture. Cloudflare's are great and I would love to see more from others in the industry.

Underneath a public statement they all have extremely detailed post-mortems. But how much goes public is 100% random from the customer's perspective. There's no Monday Morning QB'ing the CEO, but there absolutely is "Day-Shift SRE Leader Phil"

At my first job one of my more senior team members would throw caution to the wind and deploy at 3pm or later on Fridays because he believed in shipping ASAP.

There were a couple times that those changes caused weekend incidents.

Network routes consist of a network (a range of IPs) and a next hop to send traffic for that range to.

These can overlap. Sometimes that’s desirable, sometimes it is not. When routers have two routes that are exactly the same they often load balance (in some fairly dumb, stateless fashion) between possible next hops, when one of the routes is more specific, it wins.

Routes get injected by routers saying “I am responsible for this range” and setting themselves as the next hop, others routers that connect to them receive this advertisement and propagate it to their own router peers further downstream.

An example would be advertising 192.168.0.0/23, which is the range of 192.168.0.0-192.168.1.255.

Let’s say that’s your inference backend in some rows in a data center.

Then, through some misconfiguration, some other router starts announcing 192.168.1.0/24 (192.168.1.0-192.168.1.255). This is more specific, that traffic gets sent there, and half of the original inference pod is now unreachable.

But what about when LLMs go down and a good chunk of a whole generation won't even know how to think, when the remote system goes down? (Is the ability to think "the engine" of self and agency in this metaphor?)

We are building a wildly irresponsible context to exist in.

I've often thought that local power generation (via solar or wind) could be (or could have been) a viable alternative to national grid supply.

Imagination, either the first or last thing to die in 2075.

They made pro have many times more value than paying per token and then they made max again have 25x more tokens than pro on the $200 plan.

It’s a bit like being offered rice at $1 per grain (pay per token) or a tiny bag of rice for $20 (pro) or a truck load for $200. That’s the pricing structure right now.

So while i agree you can’t easily exceed the quota on the big plans it’s a little crazy how they’ve tiered pricing. I hope no one out there’s paying per token!