lostathome

For the App Store I would need to strip off some features.

I think you reasoning is valid, but the app is open source. Worst case one can compile it (e.g. just ask AI agent even if you are not a technical user).

I also put it a low price, for this version, as I would like wide adoption. I truly believe people are going to move heavier into local AI, and it is good to have low friction entries.

On it! Thanks for the great feedback.

I wonder what clients would think if they discovered their lawyer uses a chatbot with their confidential story. Even with redaction, patterns still emerge. Certainly I wouldn't be happy in any case.

I see this as a strong case for private AI, or an in-house stack.

Or I have to be missing something.

I wonder who is dropping then. Lots of graduate students are from rich families, especially the international ones.

A few months ago I discovered a Jane Street backdoor challenge advertised by a Dwarkesh Patel podcast episode.

"Can you find subtle backdoors in LLM models trained using thousand of GPU hours?"

You have four models:

    a small warmup dormant model
    a big dormant model (M1)
    a second big dormant model (M2)
    a third big dormant model (M3)

I managed to find triggers for the small one (calculating pi stuff) and M1 (Conway game of life). But not sure about the others.

When trying to make M2 and M3 play the game of life, they do not have any idea of what is going on.

I am sharing some code to make a community effort for M2 and M3. I think I had a good direction, but it costs too much to host these on rented GPUs.

Most exciting thing for me is to use other LLMs to find patterns.

Disclaimer: I am not an expert in these things. So, take with a grain of salt claims you find.

This looks similar to things people are already building locally with Gemma4 and TTS; just a bit fancier.

Local models will catch up soon.

Context aware local AI assistant https://hitoku.me/draft/ I believe private local AI is the future for every day's use.

One of my hobbies is organizing events. I, like to think, I am pretty good at it. Main point is to create good initial conditions, then people take care of the rest.

I already disagree with the first line: competent output is not cheap. At least if defined as a final product.

- Just think about scientific research. Lots of data analysis results are not cheap to get.

- Even vibe coding is difficult: you need to think very hard about what you want.

What is cheaper now are some building blocks. We just have a new definition of building blocks. But putting the blocks is still hard.

Very useful advice on this post.