Viewing profile — mrinterweb

Exactly. There could be a lot of value for inference companies to do this. Could save a lot of money being able to hand off highly repetitive known tasks to far smaller specialized…

There is so much opportunity for purpose built models like this. Ideally a harness should spin up a subagent to offload to targeted models for specific tasks like this. I know this…

This looks fantastic for a common async workflow I use. I often use one job to fan out multiple individual http request jobs. The reason I prefer jobs for this is easy and consiste…

That ruby fiber vs go goroutine benchmark is interesting. The 4-10x memory use doesn't surprise me, but the near performance does. I'm guessing there is more of a gap with the p50.…

Look at robotics demonstrations on YouTube from one or two years ago, and compare that to where we are today. It seems reasonable to me that general purpose robotics may be able to…

Two that I use are: * Openrouter.ai for a hosted router * https://github.com/diegosouzapw/OmniRoute for a local router

The don't only host open weight models. Also, why not promote this. If Fireworks thinks this big news might convert some new business doesn't make it not true.

Open weight models are much more auditable than closed models, but could still hide backdoors that could be near impossible to detect.

Undercutting US dominance in AI is huge for China. If the entire narrative is that you have to use Anthropic or OpenAI to access a decent model, then China's AI labs are sitting on…

As soon as the K3 weights are published on July 27th, there will be many US providers hosting the model. I realize model hosting doesn't really apply to kimi work specifically, but…

I really don't want harness lock-in. I am trying to decouple myself from Claude Code now. I love the model of OpenRouter and being able to switch models at will let's your harness …

I'm a big fan of local models, and moving inference from the cloud to local machines is great, but there's a couple potential problems with this. LLMs take significant (V)RAM resou…

PC gaming on linux these days is joy these days. The main games you're likely to struggle with are games that require some windows kernel level anti-cheat software running, so some…

I few months ago, I backed up my windows gaming machine and overwrote the partition with CachyOS. Haven't looked back. Gaming performance and compatibility has exceeded my expectat…

I have a lot of hope for local AI. Local model intelligence has come so far from where it was just a few years ago. It is about a model's intelligence density now for local AI. Mod…

The biggest concern is identifying "who". If the US government says only US citizens can access a model, how do they enforce that. Anthropic and OpenAI will use Persona (a company …

I don't call people rude for doing it. Maybe I should. I consider it rude. Maybe I should inquire if the earbuds are for hearing assistance then mention they are rude if they say n…

> And people now don’t feel neglected when you keep the Pods in your ear. I disagree with this. Pods in ears are essentially a "do not disturb" sign for most people. Being around p…

MV3 is not an improvement over MV2 for the purposes of ad blocking.

This would have made my life so much easier. I wrote a medical scheduling calendar application about 1.5 years ago.

It kind of sucks, but I get the silent change. If a user was trying to use the model for something untoward, having a rejected prompt would just give signal to train on how to even…

The title is a bit misleading. The title suggests that Facebook is intentionally paying for a political interference campaign targeting Alberta. It sounds more like it is the monet…

I think devs forget how efficient and blazing fast server rendered pages can be, and ultimately what a great user experience non-SPA applications can provide. It seems like the dev…

I agree with everything except > this will create pressure on developers to memory-optimize their software Ideally, yes, realistically, no. It is rare that I hear FE devs consideri…

The Neo's value prop is great for many people. I keep needing to remind myself that most computer users can get by fine with 8GB or RAM, and that the I'm not the target market for …