I want to learn robotics too!! I have a feeling that trying to build something helpful for myself, with help from LLMs, could be a good strategy—but I have no idea! Possibly budget-friendly
It's interesting how there may be an implicit assumption that imposing more rules on tech will lead to positive outcomes. From my perspective, technology is like reality itself: very difficult to control, with countless ways to achieve the desired result while circumventing the rules. And what's the actual result? Just look at the market capitalization of European companies compared to US companies...
Or maybe it just feels good to add new rules and engage in virtue-signaling contests. Or maybe it's just a way to make everything illegal—'find me the person, and I'll find you the crime' type of control. Maybe a combination of all those. Who knows?
From my experience, the farther you get from the influence of bureaucrats, the happier life becomes...
The regulatory frameworks in the EU are intentionally not designed like the US, to maximize company profits over e.g. human rights and health.
It is thoroughly documented that social media and the modern web are designed to be addictive, by psychologists who specialize in this. We regulate access to other addictive things, because addictive things break humans' normal control systems.
> "the farther you get from the influence of bureaucrats, the happier life becomes"
only when things are "normal" and if you're a default power-holder in a community. For everyone else, really no.
> Just look at the market capitalization of European companies compared to US companies...
A huge portion of that market cap exists only because the companies in question are allowed to act unethically. Aside from that, all this wealth is concentrated in the hands of a small minority.
Ultimately the economy exists to serve us, not the other way around. What good all that market cap does for the average American?
Indeed the cat and mouse game is tedious... There's a case to be made that you should just act on the root cause of all these issues with a neutral policy tool. The best tested of all regulatory tools is taxation. Reduce the profit motive slightly and many of these aberrations nobody likes will go away.
Aren't you happy that when you buy food, it doesn't contain cocaine? Regulations are totally necessary and addictive online social media is a well documented plague in our youths especially.
This very US lobbyists narrative that Europe regulate while missing out on the economy is used and abused anytime something look like contrary to US interests in MAGA land.
> And what's the actual result? Just look at the market capitalization of European companies compared to US companies..
Europe is actually doing quite well at the moment. The European stock markets have over-performed quite decently vs. the US ever since Trump became president, despite the various curveballs thrown at Europe in recent years. Market capitalisation in the US is held up primarily by the Magnificent 7 who are great outliers in the American stock market.
Maybe the momentum of Stoxx600 will last the next 4 years? Or maybe the S&P500 will come crashing down soon? Who knows.
The Shiller PE ratio is insanely high. At least the European market isn't completely overinvested in just 7 companies who are spending a lot of their money on the exact same thing, so it has that going for it.
I started playing with skills yesterday. I'm not sure if it's just easier for the LLM to call APIs inside the skill — and then move the heavier code behind an endpoint that the agent can call instead.
I have a feeling that otherwise it becomes too messy for agents to reliably handle a lot of complex stuff.
For example, I have OpenClaw automatically looking for trending papers, turning them into fun stories, and then sending me the text via Telegram so I can listen to it in the ElevenLabs app.
I'm not sure whether it's better to have the story-generating system behind an API or to code it as a skill — especially since OpenClaw already does a lot of other stuff for me.
They're basically all trade-offs between context-size/token-use and flexibility. If you can write a bash or a python script, or an api or an MCP to do what you want, then write a bash or python script to do it. You can even include it in the skill.
My general design principle for agents, is that the top level context (ie claude.md, etc) is primarily "information about information", a list of skills, mcps, etc, a very general overview, and a limited amount of information that they always need to have with every request. Everything more specific is in a skill, which is mostly some very light touch instructions for how to use various tools we have (scripts, apis and mcps).
I have found that people very often add _way_ to much information into claude.md's and skills. Claude knows a lot of stuff already! Keep your information to things specific whatever you are working on that it doesn't already know. If your internal processes and house style are super complicated to explain to claude and it keeps making mistakes, you might want to adapt to claude instead of the other way around. Claude itself makes this mistake! If you ask it to build a claude md, it'll often fill it with extraneous stuff that it already knows. You should regularly trim it.
It seems cool! How to use it for free with acceptable quality? Also what are the alternative for a personal assistant that remember stuff automatically and message you about it?
Electronic devices are very effective distraction tools, especially phones. Companies and apps leverage our psychology and biology to get our attention, but we can take control of what we interact with—and if we remove the hooks, they won't be able to exploit them anymore.
What could help is taking control of how devices interact with us, rather than letting other people control that. This includes deciding which apps can be installed, how often they can notify or distract us, and so on.
A very basic step is using an app blocker. The ideal solution would be a phone with a local AI that is aligned with my personal preferences and instructions.
For example, it could deliver news just once a week from outlets across the entire political spectrum, eliminate social media entirely, and surface only important emails and messages at the most appropriate times.
I like iOS' "Notification Summaries" as a compromise. It's about as close to "turn all these notifications into a regularly scheduled newspaper" as we can get.
I still cull notifications that I don't think provide value (notifications are a privilege based on trust and apps that break that trust lose that privilege), but yeah even when I get notifications I only really get them once every 4 hours or so, and that's nice.
I see LLMs as searchers with the ability to change the data a little and stay in a valid space. If you think of them like searchers, it becomes automatic to make the search easy (small context, small precise questions), and you won't keep trying again and again if the code isn't working(no data in the training). Also, you will realize that if a language is not well represented in the training data, they may not work well.
The more specific and concise you are, the easier it will be for the searcher. Also, the less modification, the better, because the more you try to move away from the data in the training set, the higher the probability of errors.
I would do it like this:
1. Open the project in Zed
2. Add the Gemini CLI, Qwen code, or Claude to the agent system (use Gemini or Qwen if you want to do it for free, or Claude if you want to pay for it)
3. Ask it to correct a file (if the files are huge, it might be better to split them first)
4. Test if it works
5. If not, try feeding the file and the request to Grok or Gemini 3 Chat
6. If nothing works, do it manually
If instead you want to start something new, one-shot prompting can work pretty well, even for large tasks, if the data is in the training set. Ultimately, I see LLMs as a way to legally copy the code of other coders more than anything else
This is slightly flawed. LLMs are search but the search space is sparse, the size of the question risks underspecification. The question controls the size of the encapsulated volume in that high dimensional space. The only advantage for small prompts is computational cost. In every other way they are a downside.
Wow! Kudos for thinking it was possible and making it happen. I was wondering how long it would be before big local models were possible under 10k—pretty impressive. Qwen3-235B can do mundane chat, coding, and agentic tasks pretty well.
I feel like it's going to be a long long time before we get a repeat of something like this. And David did such an incredible job on this. Custom designed frame, designed his own water-block! Wildly great effort here.
I am not sure I am doing it the right way or if there's a right way, but what I do is generate small files one at a time, with a functional system of stateless input/output. That way I can focus first on architecture, then on stateless input/output Lego blocks, and just ask the AI to generate the Lego blocks. Like this, everything is easy to keep in mind and update and change after experiencing the tech and having emotions telling me what to change. It has been working great for me. It strikes a good balance between simple and robust, fast to build, plus easy to update. The other thing is that since I haven't spent too much energy on writing the code, it is very easy to detach emotionally from it when reality gives me new info that requires throwing out part of the system.
reply