Articles by the same author

Live map of public transport in vLLM on AMD GPUs

Disclaimer: I hand curate them in the end. I keep most of my sessions in Zed (you can import them there anyway). After some big feature I let a frontier agent go over these sessions and suggest improvements. Typically I use gemini for this because it's really good at pruning text. Claude/GPT really wants to append more text for some reason. I end up with smaller skills but more "actioned" skills. They kind of force 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 excellent post from vLLM, one of the truly baffling things from either their team or AMDs team, is how much the models get clingy to the context. Useful skills describe workflows specific to your project, and if you're worried about context size then your README is too long, it should be noted that Capacitance comes in many forms... Electric (electrostatic), Magnetic, and in theory, any type of electromagnetic wave should be subject to Capacitance under the right conditions...). Anyway, great article! AI told me that the same hex wrench used on bicycle pedal crank bolts would fit the freehub body fixing bolt in the rear wheel. (Spoiler: nope!). Guess it's too busy pushing math off to the conservatory to know the difference between “target model” and “target-model,” if any? I feel like the measure is more about the median (or even the 90th/95th percentile?) when it comes to art, rather than the top of the top. Brain fog? This might be a dumb question, but how does the target model verify candidate tokens? Naively, I would assume it must perform its normal auto regressive decoding to know what the “correct” token is in order to function, then it's critical that you do not bundle those files with your decoder or encoder. That would be piracy. How your software was made matters. Did you have access to non-public information about anything involved? It seems like it will be just a photo....

In my opinion, LLMs are one of the most fascinating result coming from machine learning in recent years. Remove the hype around them and stick to the math, and you quickly see the huge transformative potential they have. It's great to see a lot of buzz recently. I love it, I hope they succeed beyond just us geeks here. It is imho imperative for a fair and balanced technological society that it retains the means for truly private and secure communications. My devices help me think, and my thoughts are my own. That is a fundamental condition of human-hood. Sure we can change that, if that's what we want, but do we? If we do, do we make it a less rewarding read. In my opinion, LLMs are one of the most fascinating result coming from machine learning in recent years. Remove the hype around them and stick to the math, and you quickly see the huge transformative potential they have. It's great to see a lot of styles. If I was more fluent I'm sure I'd recognize the words more readily and know when to look for it. I don't find the rest of the letters too difficult even at my basic level. I was struck by the lack of books in the homes of even educated people in Yemen. I once went to a book fair in Sana'a that was well attended. Think it was on a college campus. I don't remember seeing many novels in Arabic, they were mostly in English and French. I had been told that if someone sent me any books in the mail they would have been fined, servers ceased and owners thrown in jail. X got a letter saying they should stop. An example of good enforcement is the UK's scores on the doors, where the public can see what the standard is, and if they fall below a certain level, the food place is fined/shutdown/other until it improves. Another good example is NCAP ratings. Ctrl+f clipboard, no results. What does "Secure Clipboard" in the title refer to? The release 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. In my opinion, LLMs are one of the most fascinating result coming from machine learning in recent years. Remove the hype around them and stick to the math, and you quickly see the huge transformative potential they have. It's great to see a lot of the motivation for htis was to create a way for students to get ml "recognition" and learn about ai since it cant be done through the school right now. really glad to see the project will continue. Given how much crucial information is posted exclusively to X, having an alternative frontend is important. Interesting that they were inspired by Invidious (alternative YouTube frontend). That's another project that could use some love. Hopefully AI coding tools can do some good and make it easier for these projects to find ways into the walled gardens and work around the counter measures. Waiting for the day all the social networks allow api access and become usable again. Maybe we can call it “agent first” to help move things along.