nzach

I don't think this is a good marker for intelligence, but I think if you avoid dismissing issues because other people are dumb you will generally think harder and in the end will have a better understanding of the issue.

I have a personal rule that goes along the lines of "If I can't explain why a smart and kind person thinks the opposite of me it means I don't really understand the issue". It doesn't mean that I have to agree with them, but I always try to understand where they came from.

And don't forget the 'Thing' from Addams Family in the shoulder of the guy on the left.

My guess would be that somewhere you have these instructions being fed to the agent. Double check skills, AGENTS.md, memory, agent definition...

You can also ask why did he mentioned something that wasn't done or why he thought this was important.

In my AGENTS.md file I have an instruction telling the agent to never commit any changes unless I explicitly ask for it, and this leads to messages similar to what you just described.

I'm starting to think that 'memory' may be the wrong analogy for what we want.

I do think that having a set of token that are highly personalized to your project and to way you work is beneficial. I also think that the idea that this set of token will be constructed in the background without any work from the user is really appealing. So it's understandable that the 'memory' analogy became so popular.

But in my experience having a really good AGENTS.md file almost always produce better results than enabling memory.

Maybe we should start to think about how we 'train'/'onboard' agents into our projects, in a similar way that we do for new co-workers. Imagine if we could send the agent to our repo and ask it to learn our patterns and in the end we could quiz the agent to gauge how much it actually understood the project. Once he 'understands' the project we can start to use it to help with development.

In a very small scale (example, individual new features) I will sometimes ask the agent to explain me how things work (even though I already know how it works) so I can 'prime' the agent context with good data before starting any real work. But I'm not sure if this approach could be reliably scaled to work with any repo for any kind of work.

>I suggest groupthink is a critically important aspect of most human behavior. And yet somehow, we rarely manage to discuss this, and are repeatedly surprised by it. I'm unclear on why.

Isn't that just a manifestation of the 'Blind spot' from Johari Window?

In general it is really hard to think about the things you already internalized.

I really don't understand their thinking here. Sure they want more money, I get that.

But 'physical media' is one of the reasons why a lot o people make a distinction between PC and console games. Removing this will make it easier for consumers to compare a PS5 to a Steam machine, and I don't think that is a good thing for Sony.

I'm thinking about getting an Audiocast M5[0]. It seems to do exactly that. The price seems to be around US$ 30.

[0] - https://audiocast.io/

He uses the rumble to move the controller to the charging puck in a flat surface. He uses a camera to identify the direction we need to move the controller. When the controller gets close enough the charging puck automatically attaches to the controller because of the magnetic force.

Instead of training the model to directly answer questions we trained the model to always write and execute the code that would solve the question ?

If that is the case, this isn't just a fancy way to perform prompt optimization?

You could put this captcha in a location that wouldn't be very visible for a human, but if the LLM is looking at the HTML he would find this form.

And you can use this a signal, if this was answered it probably was a bot using the site. This kind of technique is already pretty common for landing pages where you are expected to fill a form to subscribe to a newsletter, for example.

I think the main advantage is adaptability.

Imagine you have a pretty exotic task you need to complete that involves converting a video file from one format to another.

You can use ChatGPT or something similar and the best you will get is either a script you can run on you machine that does what you need or he may decide to render a new video.

If you have something like OpenwebUI you could configure a MCP that converts videos and allow the model to use this MCP to do your task. This should work, but is quite a lot of work for something you'll ever do once.

But if the agent has it's own environment he can decide to install ffmpg, execute the transformation and serve you the file you want.

In reality there is no new capabilities with this approach, but things get a lot more comfortable.

Sure, I don't want an agent watching MY screen. That's why I gave him his own environment, and pretty quickly he discovered that you can open chrome and make it render to a framebuffer, this way he is able to 'view' the website. And apparently with this he is able to bypass a lot of 'anti-bot' measures.

> Computer use is such a terrible idea. It's slow, insecure, error prone, expensive.

And yet having an agent able yo use a computer on your behalf is really useful.

Recently I gave a Nix OS vm to my hermes agent and it has been a good experience. I don't really care if destroy the machine I can just rollback to an earlier version, and for any meaningful data he creates for me I make sure he creates a repo, commit and pushes to my private Gitea instance.

U$ 619 for the black and white model and U$ 719 for the color model

https://www.crowdsupply.com/modos-tech/modos-flow#products

This link is way more interesting than the original ieee.

It was submitted to HN 2 times already but unfortunately it flew under the radar: https://hn.algolia.com/?q=https%3A%2F%2Fwww.youtube.com%2Fwa...

For the last month I've worked on a firefox plugin that allows me to send webhooks to my home assistant.

In my living room I have a linux pc connected to my TV and I'm using this in 2 ways:

- Automatically set lights when media starts/stops playing. This way I can turn on some accent lighting when I pause a movie to go to the bathroom and automatically turn them off when I resume the movie

- When media is playing I calculate the color that best represents the content and export it to home assistant use it as a poor man 'ambilight' with a led strip strategically placed behind my TV

I think the next logical step is to find a way to automatically track the content I'm watching so I can have some high level stats about my viewing habits.

> LLMs make it really easy to misunderestimate the complexity

In my experience this is a real problem. Just yesterday I asked my LLM to create a piece of software that could help me build an 'ambilight-like experience' through my home assistant. It did something that seems to work as I expected, but there is a lot of theory that I just brushed past. It would be pretty easy for me to assume that I would be able to replicate this feature from scratch 'now that I understand the problem'.

Do you have any code/insights about this home agent you could share?

I'm thinking about creating something pretty similar, I want a digital housekeeper that keeps an eye on what is happening in my house and notifies me about dead/unreliable devices, fix broken automations, suggest new automations based on sensor data, etc...

I've setup the unofficial home assistant MCP already, but LLMs seems to struggle a bit to use it properly and I haven't looked into it yet to understand what is happening.

I've created lots of small things, but the most interesting is a firefox plugin that detects when some media is playing and send an event with the details to my home assistant. This way I can create some automations that automatically change the lights when I play/pause some media. It's really cool to have your lights automatically dim when you start watching a movie and then for some accent light to turn on when I pause the movie to go to the bathroom.

I went in expecting to find 'branch prediction'[0] as the answer, but apparently things are even more complex nowadays.

[0] - https://stackoverflow.com/questions/11227809/why-is-conditio...

> If it requires so much back and forth with the AI why on earth wouldn't you just write the code yourself?

Maybe I'm too far gone down the AI rabbit hole, but that seems a really strange take to have. If you replaced 'back and forth with the AI' with 'pair programming' or 'brainstorming' this phrase would be really strange, after all these are all techniques to sharpen your ideas. Even 'rubber ducking' is widely accepted as an effective way to go through a problem, and you can definitely use AI as a rubber duck.

For me the idea of chatting with the AI about a problem/solution is just another tool to help us work. It's not the best solution because it has a lot of downsides you should be aware while using it, but that is true for any technique including 'writing the code yourself'.

> While the law bans setting higher prices through surveillance pricing, it doesn’t address reducing prices. If a company raises its prices for everyone, and then offers individualized discounts, “suddenly you’ve arrived at the same outcome,” McBrien says.

While I agree with the intent of this law, I don't think it will be effective. If you have a system capable of jacking prices up you can just multiply this calculated delta by -1 transform that into a discount.

To effectively prevent this practice you probably need to ban any kind of personal discount. I don't think we will ever see such law, nor do I think this would be a good idea.

> enough samples that you can apply statistics to find precise locations, in many cases you can de-anonymize the IDs

I think a lot of people don't realize the power of a big enough sample size. With enough samples even something pretty innocent looking like your daily step counter could make you identifiable.

As far as I know we don't have large enough databases to make this happen in practice, but I don't think this is impossible in the future.

> More expensive clothes are usually less durable

I have nothing to back that up, but I wouldn't be surprised if this is a feature. If these luxury items are being used by the society (or at least in some circles) as a proxy for 'success'(ie having enough disposable money) it probably would be better if they we also quite fragile. This way you could distinguish between someone who received a expense gift vs someone that has money to always keep buying new items.

I'm not sure how real it this, but I've read somewhere that part of the appeal of expensive glassware was the fact that it was pretty fragile. Serving someone at your house with expensive glassware was a way to tell 'look how much money I've got'.

Just to be clear, I don't think we should get impressed/try to impress people by how much money someone has. But that is a practice as old as time, and it doesn't seem to be going away any time soon.

No, not really.

Let me put it in another way, imagine we find clay in an asteroid. Does that alone imply the existence of ceramic in other places of the universe?

We need these molecules to build build a DNA strand, but their existence doesn't imply the existence of other life forms. Maybe exists a process that produce these molecules naturally and we just don't know about yet.

And remember that life(self replicating organisms) is way more complex than just DNA/RNA. In another crude analogy you could say that DNA is just the source code, to have life you still need to have all the hardware to run this code on. (fun fact: that is the reason why people argue about virus being something alive or not. Generally it has only the RNA necessary for the replication, and this is why it can only reproduce if it is able to take over another cell. In this analogy it has the source code but not the hardware, so how do we classify it?)

> It implies life was seeded on earth and not generated via abiogenesis.

I don't think this conclusion is correct. The abiogenesis/panspermia debate is about where life formed. This article only says "we found all the DNA/RNA bases in an asteroid," but there is a HUGE gap between DNA bases and life(ie self-replicating organisms).

Making a crude analogy you could say they found Lego pieces in the asteroid, but that doesn't imply that the first 'Lego kits' on earth came pre-assembled. They might, or might not. We don't really have enough information to get a definitive conclusion. What we know is that we can't discard the panspermia idea yet.

I've been thinking about critical thought in our society from another angle. In my opinion if you assume that every person employs it's critical thinking abilities to reason about the world you would expect to see a lot of different opinions about the world.

But with each passing day we see the opposite, more and more people are converging in one of a few opinions about each topic. This is great if you want to move the world in a specific direction, but I think it demonstrates that people are exercising less their critical thinking abilities.

AI definitely made this worse, but I think it started long before that.

Another factor that I think contributes negatively to this effect is that our society doesn't really like when someone is wrong, or changes ideas. If we want to encourage to use their critical thinking skills we also need to tell them that arriving at bad conclusions is ok, the important thing is to always keep improving.

If this seems interesting for you remember that if you are putting $100 in a 99 to 1 bet you need to win 100 times to get $100 but only need to loose 1 time to loose $100.

And the chance of losing at least once in a 99% sure bet after 100 rounds is around 60%. Even if you reduce to 30 rounds it still is around 30%.

This may seem smart at first glance, but the math doesn't really checks out.

If you are willing to point your LLM to the docs instead of actually reading it why not skip it and send your LLM directly to the source code? That is what I've been doing recently, and that is why recently good documentation became less important for me.