tmaly

I only saw a contrast of Japanese World Cup vs NY Knicks

I have been reading these threads where people are patching firmware with AI. I am wondering if there is a way to fix some of the privacy issues on Roku tvs given this deal.

I would have loved to see some clones of the original Nintendo games made to work in the browser as multi-player games. The original Final Fantasy would have been cool to see.

This could be a big issue for firms with strict GDPR criteria: "This change only applies to organizations that have set up workspaces with zero data retention (ZDR) in Claude Console, use Claude Code with ZDR in Claude Enterprise, or access Claude through AWS Bedrock, Google Cloud Agent Platform, or Microsoft Foundry with ZDR. The rest of this article applies only to these organizations."

Is the project more of a private residence or something that would bring tourism to the local economy?

Our bottleneck is going to be verification.

Energy is likely more abundant in China. I am not sure about compute, but that must be part of reason for such drastic price differences.

This reminds me of the Peter / Boris comments on writing loops to keep the agents busy.

I had to buy a new washing machine last year. It has an AI mode, what ever that is. I have never used the mode.

It was last Summer. I was at an AirBnB and the fire alarm system had a fault and kept beeping.

I took a picture of the panel and the AI was able to diagnose the issue and tell me how to temporarily disable the beeping sound.

I knew nothing about fire systems. I had the owner call a repair person the next day to resolve the issue.

Recently I was trying to find a matching stain for wood flooring in a house build in 1999. I uploaded a clear picture in bright sunlight and ChatGPT was able to search online and find a matching stain color. It presented me with ordering options and I got a quart delivered yesterday.

I have been working on my own variant of OpenClaw written in go. I got the voice mode wired up a few weeks ago and it just started having a conversation with me. My wife freaked out and was asking who was talking to me.

I am trying to think of a use case for this.

I was thinking the client side WASM version would be useful as a platform for beginners to practice a subset of Python in.

I can't really think of any good WASI use cases.

I heard about the ShinkaEvolve on a podcast where the guest had used it to evolve an agent harness for a less capable model.

I ended up borrowing the ideas from it for one of my own personal projects.

I would not try to mix newbies in with experienced software developers.

Pick one audience at a time and approach it that way.

For a newbie, something like Replit free tier might be the way as there is little cognitive overhead to getting setup.

For a experienced developer, having them get a $20 sub and work on one of the popular agent harness.

the DeepSeek V4 Flash is impressive for the cost

I am surprised someone hasn't made a really nice equivalent to Obsidian for Mastadon and just released it for free on the app stores. I am sure one could host a very cheap mastadon instance on a low cost VPS

this is the new GTD

I still enjoy buying paper books and reading them. There is something different about having something physical.

Has any judge every ruled using the 10th amendment in a federal case?

I would love to see two things:

1. A new Gemini model that is not quantized.

2. A way to connect NotebookLM notebooks to any agents if you pay for the pro subscription.

Can you do one for dogs?

I think he is playing the political game and will be pro who ever is in office to protect his baby

I didn't get the AI vibe from it. At some point we are just going to have to get use to most stuff being written to some degree by AI.

There will be different shades of usage and maybe we draw a line somewhere in there.

When AI generates code, we have the ability to easily verify it and test it.

The same is not so easy with free form text. I have been thinking about this mainly around when agents write plans or edit plans, but I think figuring out how to do this in general would be a huge breakthrough.

Logical English was one idea I came across and Runcible https://runcible.com/ was another idea I recently stumbled on.

Just a cautionary case of porting to Rust using AI

https://blog.katanaquant.com/p/your-llm-doesnt-write-correct...

I remember NVIDA sponsored a TLA+ challenge last year https://foundation.tlapl.us/challenge/index.html

The intro was the best part of the README in my opinion. The rest of the README looks and feels AI generated. I am guilty of this same thing with README files.

I have been using Go since 2014. I have services that just run without issue.

Having backwards compatibility with 1.0 just makes it easier to maintain software.

The big plus in the modern era is that the simplicity of the language lends to having agents write Go without much fuss. That and the standard library being batteries include lets you direct the agent to use little or no third party dependencies.

I wonder what this model will do and if anyone can map out its capabilities?

Publicly traded companies get their stock price punished if they just announce layoffs, whereas if they say it is because of AI, they do not see the same treatment.

If you look at Coinbase in 2020 they had roughly 1,200 employees. By 2022 they had roughly 4,500 employees.

They over hired and now they are pairing back, this is all it is.

Sometimes people don't know what they want.

I prefer the start small and iterate approach to arrive at a result.

Then I ask it to summarize. Sometimes after that I ask it to generalize.