wickedsight

It feels weird/wrong that the Anne Frank Foundation of all things would fight against a free internet and battle companies that allow people to fight oppressive regimes.

This is correct. Also, the people who produce CSAM usually don't just stop, so tracking down material, especially new and unknown, is one of the most important ways to stop active abuse. Also because the material is actual proof and many (C)SA cases fail due to lack of exactly that.

This doesn't mean I agree with active scanning of things like iCloud, effectively making everyone a suspect, but counter to what people here seem to think it really might help prevent CSA.

Yeah, I kinda feel like OP is missing the fact that it kinda already is the way they described. The majority of devs are mediocre at best and work on variations of mostly the same CRUD apps for different businesses. Only a relatively small number of people work on complicated stuff that requires CS knowledge.

There's a much bigger group of people building games with Unity than the number of people building complicated engines like Unity. Same for [insert Javascript framework here].

I get what you're saying, but I'm guessing that people asking how to pee is a drop in the bucket compared to the agentic loops being called to rename some variables across a project.

I'm one of the people who mostly ignores his videos due to their length and the 'old man angry ranting about things' vibe they give me.

Yup, the nerds are still here. They're people like Jeff Geerling, Stefan Hermann, Andreas Spiess, Jan Roetz and many more. They're very visible if you end up on the 'right' side of the algorithm, it's a much more positive side of the internet in general IMHO.

But it's easy to slide back into the fear mongering, engagement bait side if you don't pay really close attention to how you're feeding the algorithm.

I feel like the others didn't understand the part where you weren't into AI lingo. You're correct, this is like having a memory for an LLM, because an LLM is stateless.

When you chat with an LLM, there's a concept called 'conext'. In essence, context is feeding all previous messages into the LLM together with your latest message. Because context is essentially a finite resource (it requires system memory and increases processing time) the bigger AI providers use tricks to compress context.

These providers usually also have 'memory', which in essence is just parts of previous chats that are entered into the current context based on their relevance. I don't know exactly how this works, but I'd imagine that it does some search for related chats and then adds summaries of those.

In essence, this tool allows you to do those things locally. This allows you much more control of what history the LLM gets and therefore the 'context' it works with. This is important, because context can get dirty. You can notice this if you're chatting with an LLM, it goes completely the wrong way, you try to get it on the right track again, but it just won't. That's because it just tries to predict the next word based on the full context and it might end up consistently predicting the wrong next word.

The annoying thing is how many businesses and communities rely on Meta platforms

During local elections over here (Netherlands), it was impossible to find any info from local parties outside of Facebook. Those parties are also the biggest, usually. I ended up voting for the one party that had a website with their plans for that exact reason.

The polarization comes from the very disparate coding experiences and output quality that different people find when using these tools.

Not just when using tools, also when using humans. The frame of reference of what is considered 'production code' differs immensely between organizations, teams and people. The code I get from LLM's is usually much better than what I get from my peers. Maybe not one shot, but after some steering it gets there.

It also isn't lazy. When generating test cases for relatively simple pieces of code, it usually tests pretty much every path and doesn't stop right at the 80% code coverage quality gate.

I can imagine if you're at the level of Linus or something, you might conclude differently, but most people aren't there at all.

While I understand where you're coming from and that this thinking is probably (and somewhat understandably) why there are no water filling stations, I find this incredibly nasty. I don't want to fill my water bottle in a public restroom riddled with bacteria.

And yes, I'm fully aware that a water filling station will probably be just as nasty, but it's the thought that bugs me.

Not sure which exact model you're talking about, but I've run the 30B and the 3.5 32B models and both can get some things done and can waste tons of time getting some things completely wrong.

They're fun to mess around with to figure out what they can and can't do, but they're certainly not not tools in the way I can count on Codex.

Where/how do you host your family apps to have them conveniently available to your household? This is the thing I'm struggling with most.

Who is served by persisting these sessions? I would suspect that there is little reason why future engineers, or future LLMs, would need access to them

I disagree. When working on legacy code, one of my biggest issues is usually the question 'why is this the way it is?' Devs hate documentation, Jira often isn't updated with decisions made during programming, so sometimes you just have to guess why 'wait(500)' or 'n = n - 1' are there.

If it was written with AI and the conversation history is available, I can ask my AI: 'why is this code here?', which would often save me a ton of time and headache when touching that code in the future.

have lost quite a bit of reputation

in the tech world, maybe. All my 'normie' friends are using ChatGPT though and have no concept of their reputation, nor intention of switching. Most people I know are hardly even aware of alternatives, even of Gemini, though everyone has a Google account.

I personally also use ChatGPT and have zero reason not to, currently. I might switch if they royally mess up, but everything they've messed up has been fixed within a day.

Do you think 30% of your friends or family members can't answer this question? If not, do you think your friends or family are all better than the general population?

That actually would be quite feasible. Intelligence seems to be heritable and people will usually find friends that communicate on their level. So it wouldn't be odd for someone who is smarter than the general population to have friends and family who are too.

You could just, you know, Google the list.

It's about making people feel safe.

My guess it's more about being able to say: 'We did everything we could.' If someone does end up getting a bomb on board. If they didn't do this, everyone would be angry and headlines would be asking: 'Why was nothing put in place to prevent this?'

Even less users know how to do this with an executable.

How confident is the OP that every single one of these 60 calculators work all the time, with all edge cases?

The compound interest calculator, which is their 'favorite page', already shows an incorrect value in the graph. So my faith in the other calculators isn't great. I also kinda doubt OP's story of them using that page all the time, since it took me about 20 seconds to find this issue.

I can easily check network monitor in the browser to see exactly what a web app is doing.

Running an executable is a risk by default and the way it interacts with my network is way less transparent. I honestly prefer this in the browser.

I don’t work in big tech. Wish I was, would be a pretty big improvement in my salary. Still think I’m very spoiled compared to about 90% of the world, probably more than that.

when push comes to shove the EU can force banks in the EU to uphold EU rules and regulations.

This made me realize that many people who are extremely critical of the power the EU has, have no idea how much that power is often protecting them.

This is not a dismissal of the fact that it's absolutely critical to stay vigilant about how that power is used. But it's quite clear that without that power, the US would've abused theirs way more within Europe.

His alternative of not working for big tech is literally the only way out of this.

This won't actually work though. The only reason we even have this discussion is because we're rich enough that pure survival isn't even really in our instinct anymore. Most of us haven't experienced actual hardship for years and we live in luxury.

There are plenty people in the world who are smart and poor and living tough lives, who are ready to replace people who quit because they have te luxury to quit. Just look at the huge amount of Indian people moving across the world to work in tech. These people aren't going to let the opportunity to significantly improve their lives go because they're going to work on software that might negatively impact society at some point. You could see this exact thing happen when Elon took over Twitter. Many people left because they disagreed with Elon, while many H-1B stuck around because they (and their families) actually had something to lose.

I don't think many of us on HN realize how incredibly spoiled we are with the lives we live.

I'd like to understand what a real, good alternative is.

The "real, good" part all depends on your expectations of life.

There's a real shortage in trades people and I'd love to see ChatGPT fix a leaky pipe, build a house or make a chair. So switching to the trades/manual labor, while financially tough at the beginning might be a good long term choice. But this requires much more physical work than most of us on HN are used to.

Moving away from capitalist society into a cheap tiny off grid house in a rural area and leading a much more basic life is also an option. You don't need 100k to survive, but you do need it in populated areas. (Also, I'm European and therefore not dependent on employment for health care, so I'm ignoring that part.)

There are many choices we can make that remove our dependence on big tech. But big tech is hella convenient and so is having expendable income, so it's a tough choice to make.

I find it interesting you're all writing 'the AI' as if it's a singular thing. There's a myriad of ways to code with a myriad of AI's and none of them are identical. I use a Qwen 3 32B with Cline in VSCode for work, since I can't use cloud based AI. For personal projects, I use Codex in the cloud. I can let Codex perform some pretty complicated tasks and get something usable. I can ask Qwen something basic and it ends up in a loop, delivering nothing useful.

Then there's the different tasks people might ask from it. Building a fully novel idea vs. CRUD for a family planner might have different outcomes.

It would be useful if we could have more specific discussions here, where we specify the tools and the tasks it either does or does not work for.

Sometimes it's pretty great and pops a video with only a few views into my feed that totally fits my interests. Sometimes my entire feed is Kitchen Nightmares episodes because I happened to watch one or two yesterday.

I feel like it's more because the detractors are very loudly against it and the promoters are very loudly exaggerating the capabilities. Meanwhile, as a bystander who is realistic and is actually using it, you have moments where it's absolutely magnificent and insanely useful and other moments where it kinda sucks, which leads to the somewhat reluctant conclusion that:

The productivity gains from LLMs are real, but not in the "replace humans" direction.

Meanwhile the people who are explicitly on a side either say that there are no productivity gains or that nobody will have jobs in 6 months.

The VM still needs access to the network for the use cases they described though.

How did you make sure Claude wasn't doing anything unintended while allowing it to run scripts it wrote on your network?

Does anyone have any good advice or resources on a good workflow to do this with web apps? There's some stuff I'd really like to solve, for myself/family, that would require a front and back-end with persistent storage.

I would love to easily be able to set this up easily when a new idea pops into my mind and then have something running (locally or securely in some cloud) within a few hours/days. I wouldn't want to spend a ton of money for this though, nor have a lot of overhead to manage.

Edit: In addition, I'd like some safeguards where I can't have the LLM of choice accidentally delete stuff or do other unintended things on my network.