LLMs write. It sounds glib but it's what they do, and so every problem they encounter they will try to write their way out of it without lots of hand holding.
There are a good number of instances of western companies doing just that. The sony rootkit kerfuffle comes to mind, and that one esports company that put a bitcoin miner in their anticheat software for counterstrike…
I personally really do think we are headed toward a world where stuff is hyper customized like that. As a developer, it already feels like this with internal company tooling. Anything I have the source code to and a…
And I pay taxes and some non-zero amount of that money is going to Musk through various channels. I'm still never going to use an xAI product.
https://en.wikipedia.org/wiki/Sony_BMG_copy_protection_rootk... As the saying goes, this is what radicalized me. If any one of us did anything close to this we would be treated like Aaron Swartz and given a 35+ year…
I've been having a fantastic time telling it to use ASD-STE100 Simplified Technical English (or use a skill for it, I've been playing with [1]) It's a very clear and understandable way of writing that puts priority on…
I'm actually finding Luna to be an extremely strong model in practice. I almost exclusively use it with xhigh or max effort, but when run like that it's been an incredibly cheap little workhorse for most development…
I feel like we have the technology to prevent a car from starting if the driver is significantly impared, but "solving" addiction, cancer, and heart disease are much harder problems. Obviously it would need to be…
If they're using a static threshold of 200 views and there aren't many of these left it could pull them all out of that category. It could obviously be fixed but I was more curious than anything
AES is so cheap with hardware acceleration that I could see an argument that it prevents casual sniffing of the traffic. Personally I think the false sense of security would outweigh those benefits, but I'm not in their…
Yeah it wouldn't have changed this specific case but still why use it? It's slower even without AES NI!
Is there any valid reason to still be using 3DES in 2026? It was formally deprecated in 2018 and has been surpassed in just about every single way by AES long before that. At this point I feel like it's use is such a…
I also have no idea what I'm talking about, but to me this seems closer to the "caveman mode" that some people use to compress info into fewer tokens. Going through the image tokenizer allows you to leave the source…
That's like saying quantization isn't real because the frontier labs aren't using it in their production inference. This is a lossy process, it produces worse results. It might be worth it for some situations, but…
This is what I'm advocating for. Give each dev's AI agent its own identity with its own access controls and tokens and everything. It helps solve both the access control and attribution issues
There have been a few instances, IIRC there was an Apollo mission that had a head cold spread among the whole crew. But that's unlikely to be the case here because they've been up there isolated for over 6 months now
And if you like it, picking up any QMK or ZMK compatible keyboard would let you do it in firmware too!
> For code modifications in a large codebase the problem with multi-shot is that it doesn't take too many iterations before I've spent more time on it. I've found voice input to completely change the balance there. For…
If the LLM is able to handle it why do you need to maintain those specific skills?
Given it's passing retrograde (is that even the right way to say that?), would that make it easier to catch up and intercept? Assuming you don't want to do anything but fly by or smash into it
> We propose adopting diffusion language models for text embeddings, motivated by their inherent bidirectional architecture and recent success in matching or surpassing LLMs especially on reasoning task. I didn't…
LLM autocomplete is an entirely different beast. Traditional auto complete can finish the statement you started typing, LLMs often suggest whole lines before I even type anything, and even sometimes whole functions. And…
So is the big improvement here simply skipping the unembedding/embedding step for internal thoughts? Or is it mainly in the training methods to teach the CoT and how to switch between "latent thought" and text output?…
I've been loving Copilot Edits (their take on the multi file edits stuff). I'm personally still doing the process of finding and adding files to its context/working set (letting it try to do that part just doesn't work…
The one that gets me is the issue they found while testing gpt-4o where it stopped mid sentence, shouted "No!", then cloned the users voice and began speaking as them.…
LLMs write. It sounds glib but it's what they do, and so every problem they encounter they will try to write their way out of it without lots of hand holding.
There are a good number of instances of western companies doing just that. The sony rootkit kerfuffle comes to mind, and that one esports company that put a bitcoin miner in their anticheat software for counterstrike…
I personally really do think we are headed toward a world where stuff is hyper customized like that. As a developer, it already feels like this with internal company tooling. Anything I have the source code to and a…
And I pay taxes and some non-zero amount of that money is going to Musk through various channels. I'm still never going to use an xAI product.
https://en.wikipedia.org/wiki/Sony_BMG_copy_protection_rootk... As the saying goes, this is what radicalized me. If any one of us did anything close to this we would be treated like Aaron Swartz and given a 35+ year…
I've been having a fantastic time telling it to use ASD-STE100 Simplified Technical English (or use a skill for it, I've been playing with [1]) It's a very clear and understandable way of writing that puts priority on…
I'm actually finding Luna to be an extremely strong model in practice. I almost exclusively use it with xhigh or max effort, but when run like that it's been an incredibly cheap little workhorse for most development…
I feel like we have the technology to prevent a car from starting if the driver is significantly impared, but "solving" addiction, cancer, and heart disease are much harder problems. Obviously it would need to be…
If they're using a static threshold of 200 views and there aren't many of these left it could pull them all out of that category. It could obviously be fixed but I was more curious than anything
AES is so cheap with hardware acceleration that I could see an argument that it prevents casual sniffing of the traffic. Personally I think the false sense of security would outweigh those benefits, but I'm not in their…
Yeah it wouldn't have changed this specific case but still why use it? It's slower even without AES NI!
Is there any valid reason to still be using 3DES in 2026? It was formally deprecated in 2018 and has been surpassed in just about every single way by AES long before that. At this point I feel like it's use is such a…
I also have no idea what I'm talking about, but to me this seems closer to the "caveman mode" that some people use to compress info into fewer tokens. Going through the image tokenizer allows you to leave the source…
That's like saying quantization isn't real because the frontier labs aren't using it in their production inference. This is a lossy process, it produces worse results. It might be worth it for some situations, but…
This is what I'm advocating for. Give each dev's AI agent its own identity with its own access controls and tokens and everything. It helps solve both the access control and attribution issues
There have been a few instances, IIRC there was an Apollo mission that had a head cold spread among the whole crew. But that's unlikely to be the case here because they've been up there isolated for over 6 months now
And if you like it, picking up any QMK or ZMK compatible keyboard would let you do it in firmware too!
> For code modifications in a large codebase the problem with multi-shot is that it doesn't take too many iterations before I've spent more time on it. I've found voice input to completely change the balance there. For…
If the LLM is able to handle it why do you need to maintain those specific skills?
Given it's passing retrograde (is that even the right way to say that?), would that make it easier to catch up and intercept? Assuming you don't want to do anything but fly by or smash into it
> We propose adopting diffusion language models for text embeddings, motivated by their inherent bidirectional architecture and recent success in matching or surpassing LLMs especially on reasoning task. I didn't…
LLM autocomplete is an entirely different beast. Traditional auto complete can finish the statement you started typing, LLMs often suggest whole lines before I even type anything, and even sometimes whole functions. And…
So is the big improvement here simply skipping the unembedding/embedding step for internal thoughts? Or is it mainly in the training methods to teach the CoT and how to switch between "latent thought" and text output?…
I've been loving Copilot Edits (their take on the multi file edits stuff). I'm personally still doing the process of finding and adding files to its context/working set (letting it try to do that part just doesn't work…
The one that gets me is the issue they found while testing gpt-4o where it stopped mid sentence, shouted "No!", then cloned the users voice and began speaking as them.…