The description in the front-matter (at the top of the skill markdown file) is the only thing in the context and used by the agent to determine when to read in the rest of the skill file.
You essentially see the desktop version zoomed out by default with tiny text. You need to zoom in, but the line length is still desktop sized so you need to scroll left and right as well as up and down to read it.
And mobile browsers keep this defective by design default even they now all have an actual desktop mode that does pretty much the same thing but more consistently.
I think the idea is that it gives a bit of time for the companies which run automated scans of new versions to run through and detect any issues with new versions before users install them en-mass.
Why does it need millions of users to be useful to the individuals which use it? It's not a social media site, so I don't care how many other users they have as long as it's a sustainable business for them to keep providing a service to me.
As someone who lives on a residential street right by a primary school in the UK, the majority of drivers are going over 20mph even at the peak time when there are children everywhere.
While in theory human drivers should be situationally aware of the higher risks of children being around, the reality is that the majority will be in their own bubble of being late to drop their kid off and searching for the first free spot they can find.
the human driver would usually drive more closely to the centerline of such a residential road. If the road is clear ahead i'd drive almost over the centerline of the road having enough clearance between my path and the parked cars for any such "jumper" to be visible long enough for me to react. If there is an opposite traffic i get back strictly into my lane and slow down much more if the parked cars are close and they block sidewalk view, etc.
The autonomous cars have really got more aggressive recently as i mentioned before:
I have a similar school drop-off, and can confirm that the cars are typically going around 17-20mph around the school when they're moving. Also that yes, human drivers usually do stay much closer to the centerline.
However, Waymo was recently cleared to operate in my city, and I actually saw one in the drop-off line about a week ago. I pulled out right in front of it after dropping my kid off. And it was following the line of cars near the centerline of the road. Honestly its behavior was basically indistinguishable from a human other than being slightly more polite and letting me pull out after I put my blinker on.
> the human driver would usually drive more closely to the centerline of such a residential road
I certainly do this. But asserting that most humans would usually do this? Have you ever actually seen humans drive cars? This is absolutely not what they do. On top of that, they run stop signs, routinely miss pedestrians in blind spots, respond to texts on their phone, or scroll around on their display to find the next song they want to put on.
I vividly recall a shot within a commercial, in which a driver was shown in slow motion, chucking his coffee into the passenger foot well in order to have two hands on the wheel for an emergency. I don’t remember what was about to happen to the car or the world around it. I’m pretty sure that a collision occurred.
This is great and similar to what I was thinking of doing at some point. I just wasn't sure if it needed to be specific to Sweep Local or if it could be a generic llama.cpp provider.
I was thinking about this too. Zed officially supports self-hosting Zeta, and so one option would be to create a proxy that uses the Zeta wire format, but is packed by llama.cpp (or any model backend). In the proxy you could configure prompts, context, templates, etc., while still using a production build of Zed. I'll give it a shot if I have time.
If you lease a car the owner of the vehicle isn't the driver, but the lease company itself. Tesla was contacted to provide the drivers name (as is their legal obligation) and when they didn't they were fined.
Exactly the same is true if you own the car outright. You as the owner of the vehicle will be contacted and asked to provide the details of the person who was driving at the time.
I just realized something: doesn't this allow the actual drivers to escape the non-monetary penalties?
In the UK, if a driver is caught speeding, they'll (generally) also get points on their license and after accumulating 12 points, they'll (generally) lose their license for a while. Points decay on some frequency which I forget.
Anyway, what's to stop someone from driving a company car and then just paying the fines via the company and refusing the name the driver?
> Anyway, what's to stop someone from driving a company car and then just paying the fines via the company and refusing the name the driver?
In Germany when that happens and the company cannot (or does not want to) name the driver... they may get ordered by the authority to keep a logbook. And such an order shows up at any police checkpoint - and if the cops run the plate, they will ask for the logbook. And check the logbook. And if the logbook isn't up to speed... that means some hefty fines.
Germany isn’t required to keep a log book? In Netherlands we had to keep details on clock, distance, driver, and reason for all use of the company vehicles.
The current implementation is HTTP-focused as that was the primary use case. TCP tunneling is possible architecturally but not something I've had in mind. I suggest start by raising an issue on GitHub and adding thumbs up. If it receives enough attention, I will prioritize it. I am less familiar with what would supporting UDP entail, so cannot answer that right now.
There are other tunneling solutions that support both and https, websockets using ssh tunnels for the communication. For example I use https://tuns.sh which is a managed sish instance
Yes, negative is rare, but I wouldn't say that it's overwhelmingly expensive.
The median range is 15p-20p (60% of the time in December) and the UK "price cap" is about 26.35p.
With a tariff like that, shifting usage outside of 4pm-7pm can lead to massive savings. With our usage from the Octopus API, I can see from OctopusCompare that in the past month my effective average unit cost would be 19.24p/kWh, and we don't do any specific load shifting.
The description in the front-matter (at the top of the skill markdown file) is the only thing in the context and used by the agent to determine when to read in the rest of the skill file.
reply