EDR software on the laptop controls what is and isn't allowed. It'll be disallowing USB removable storage devices etc, while still allowing standard HID (keyboard, mouse).
They can even block all but allow-list certain vendors and models, but because USB is an unauthenticated standard - an attacker can easily spoof any vendor or model. So best not to rely on that and instead block all of certain types of USB device.
Also France is around 7c (euro) per kwh from nuclear generation. If the whole west was all in on nuclear for last 50 years it would have resulted in lower per kwh costs.
What would solar's cost per kWh be? GP means the cost of the asset per peak generation power. 0.1/W seems about right, to an order of magnitude at least.
For some reason though on openrouter the tps of 6.1 sol ultrafast is usually lower than opus 5.5 fast. Is there readings off as surely cerebras hardware is faster than low user density nvidia still?
GPT-6.1 Sol Ultrafast also uses Nvidia hardware, not Cerebras, just far better provisioned vs how they usually provide inference allowing for higher throughput.
"Much better provisioned" might be overselling it. Mainly they are just serving very few customers per Nvidia GPU, which is an expensive solution to the problem.
I do wonder where europe-north2 ("GCP Stockholm") actually is. I have not found anywhere in Stockholm with less than 5ms RTT to it. Sure, fibre is not in straight lines, but 5ms/2 is a LONG distance.
Context needs to pre-filled into a GPU memory in a node (usually 8xB300 or 8xH200) so there isn't any context or cache sharing between model families given their different parameter sizes, tokenizers, unlikely they are co-located in the same node.
Sub-agents not sharing context is a useful design-pattern when you want adversarial or independent reviews.
Cache reads could be shared between sub-agents, A single node(8GPU cluster) supports few hundred concurrent user sessions, that all share the same KV cache memory, so it is likely model providers do colocate your sub-agents in one node, it is more efficient , but may not be guaranteed so performance could vary; like we have with elastic compute and storage[1]
This can be cheaper depending on your coding flow i.e. cache hit % and the billing plan - cache reads are basically free or charged very little in subscription plans.
[1] Modern AWS does offer collocation at additional costs for compute but that is not the default and most other clouds do not offer it
Subagents don't share context. But that's why delegating implementation to a subagent doesn't work well except for things that are truly mechanical in nature: the subagent needs to independently reason about the task it is given, and then the output will also be reasoned about by the main agent. So you end up wasting time and tokens.
On the contrary, subagents save context overall, when the task is sufficiently large.
Also, my experience is that Fable 5.1 is very good at prompting/orchestrating Opus/Sonnet subagents when working on a larger task (e.g. 1-2M context window use only for the orchestrator itself).
reply