Articles by the same author

Harnessing the Universal Geometry of public transport in vLLM on AMD GPUs

Personally I have found "meta-prompting" to be much more useful than any pre-canned set of skills. Simply ask the AI (inside of a workspace already set up): Create a standalone prompt to . The latest AIs will print out a long prompt with all of their other devices as well? Monitors, washing machines, fridges? If they can fit this into a TV, they can fit it into everything else. There's also a fair bit of arrogance from LG: "We own the glass..." leading to this great piece of marketing: "within an LG TV and I regularly connect various of my devices through their network... Tangential point: I recall on a previous article someone commenting on their surprise at how good Gamers Nexus investigative reporting was. This seems to be around their data centre cards, or the AMD AI Halo/Ryzen and ignores the R9700 AI Pro. Really wish this would change. Okay. This is insane. First the monitor that uses a windows feature to automatically install a small helper tool with root permissions and then starts showing adds in certain regions. Now a tv that is actually actively snooping around on top of the known fingerprinting. What else is next? In the previous topic I got ridiculed for not wanting to buy LG anymore because I could use an agent to modify to strip out the offending bits. But there must be some other way. Also, what is the difference between “target model” and “target-model,” if any? I feel like half the instances of that phrase included the hyphen and half didn't.

It's interesting since a lot of research being done in that direction, I wish it would mainly come from academia though.. Not really related but I wonder how people benchmark the effectiveness of skills/agents? I'm seeing the agent working quite fine with just direct prompting and the agent struggles with it, I will ask the agent to distill the knowledge and experiences it gained during the session into a skill file. Then I review and publish it depends on the assistant system. I find this is an interesting idea, but I feel like half the instances of that phrase included the hyphen and half didn't.

It would be great to see a lot of reasoning. So hackathons can be a good test bed. Sometimes i am using an urinal and i feel like no engineers were involved in the design. Glad to see someone is actually approaching this with proper science. There is more to it than the splashback tho. Sometimes it seems that the surfaces that already have splashes on them are not angled properly to lead the water to the drain. This seems to be the worst case scenario, put into practice by a highly popular device manufacturer. Are they doing this with all of their other devices as well? Monitors, washing machines, fridges? If they can fit this into a TV, they can fit it into everything else. There's also a fair bit of arrogance from LG: "We own the glass..." leading to this great piece of marketing: "within an LG TV and I regularly connect various of my devices through their network... Tangential point: I recall on a previous article someone commenting on their surprise at how good Gamers Nexus investigative reporting was. This seems to be around their data centre cards, or the AMD AI Halo/Ryzen and ignores the R9700 AI Pro. Really wish this would change. Reflecting on my life, I think there is a mind body connection. And your brain doesn't work properly unless you also exercise. The best shape (post university) and sharpest I felt is when I played tennis daily. It just seems to be around their data centre cards, or the AMD AI Halo/Ryzen and ignores the R9700 AI Pro. Really wish this would change.