I read a lot of these posts that sadly leave out the basic parts: what were your prompts? What does it means in this context ‘vibe coding’? Did you create an initial setup, and slowly build up? Did you left wverything to the agent understanding, and just pushed approve or reject? There are multiple levels of quality that depends on the input. Did you get into context rotting? 3d math means vector math, matrices, or what? Given claude has a serious problem from march at least, the way u use it is paramount. In our team we all use claude with copilot ( sadly, that is a business directive ), and while excpetional at finding small relationships in components and microservices, had to build a long list of skills just to be barely usable in a ‘star trek’ way. The bottom line is that it is that you must be extremely precise when asking. Prompt modeling count a lot. Context build as well. For now, unit tests and data/mocks refactors are working extremely well for me, when i define the tests cases. My agents got to a point where i can safely have small peoperty additions with refactors on multiple repositories at once ( ie: i change the contract on microservice a, microservices b,c,and d are automatically updated ). This last part had to.be built thoug, with memory, engrams, and some fune tuing. It is not always a shit: if not nobody would use it. It is not this revolutionary technology that will make humans obsolete as well ( as they are selling it ).

I work with some data sciencetists and ml engineers on web projects. They might be good at etls, fine tuning etx, but dont let them touch anything with a public.layer or infra constraints.

How you deal with critical vulnerabilities on your system? Do you work with high confidential data and have openclaw os those system? How many medical devices did you have to secure from mass incursion?

How could any person with some programing literacy event thinking about installing openclaw. A malware ridden by critical bugs

Use a vpn and albanian version of.youtube

Economic growth cited by google is goole’s revenues. Also, there is no faster tech advance than in open source.

I installed Ubuntu on my father in law laptop years ago and it is still kicking. ( he’s 85 this year) He does whatever he was doing before. My smallest which is 12 has zorin installed in her first peesonal pc and never asked any help. I think that the response greatly vary by the use of the computer you have.

I recently had an hook to get some investment for a startup. Money is flowing in this sector. The investor told me: find me any idea that might sell, be useful.

I went to speak with 3 associations of entrepreneurs in 3 different countries. Like guys, we have the money, give me some ideas, all services will be free for.you. All these entrepreneurs did not know where to fit AI if not for some support chat.

Several flaws here: dependomg on the tasks, you can train and retrain models. Instruct new ones. Previous errors will be greatly reduced, or disappear completely. ( if we talk about errors only ). Hallucinations are mathematically certain for less specialized models, but this is another problem all togheter.

Using ai is indeed saving money ( and time ). It excels at tedious tasks with well defined constraints. This saves me so much time everyday: ie: find X in dataset Y that do not much Z. This work was usually done by humans, with an higher error rate. If I take 3 minutes to classify 1 millions rows, which would have took me at least 3 days before, that is money saved.

This said, they trying to push the reverse centaur approach, human overseeing the ai worker, which is flawed. But companies reason in stakeholders profit and 3 months windows.

When I started as a junior i was the guy classifying 1 M records. That is how I leaned. Now we dont have juniors anymore. But companies seems to dont care about the next 5 years.

I work in AI and the only obvious profit is the ability to fire workers. Which they need to rehire after some months, but lowering wages. It is indeed a powerful tool, but tools are not driving profits. They are a cost. Unless you run a disinformation botnet, scamming websites, or porn. It is too unpredictable to really automatize software creation ( fuzzy is the term, we somehow mitigate with stochastic approach ). Probably movie industry is also cutting costs, but not sure.

AI is the way capital is trying to acquire skills cutting off the skilled.

Have to say though that having an interfacd that understands natural language opens so many possibilities. Which could really democratize access to tech, but they are so niche that they would never really drive profit.