Get money from donors. Wikipedia shows how that can be done. Or get money from the EU.

Mozilla is a strawman for google that they can claim there exists another browser that is not chrome because of antitrust laws. And now that Microsoft forcefeeds win11 user with Edge it will not take long and google doesnt need firefox anymore.

For sure I would give a donation to firefox if they would build a decent browser which listens to the user but not as they do now.

just my 2 ct

And a lot of companies and developers would like to pay as well imho. Wikipedia or The Guardian newspaper are really good in getting money from donors.

Does it run on M5Stack Tab5 or the CARDPUTER? Did anyone try?

Oh that would be cool. The current list of hardware has two boards. So the answer to your specific question is "No."

You might want to look at upyOS all it needs is micropython running. https://github.com/rbenrax/upyOS

I've added this to my "try someday list"

I see it at our place that seniors get more productive but also that juniors get faster on track and more easily learn the basics that are needed and to do basic tasks like doumentation and tutorial writing. It helps both groups but it does not make a 100x coder out of a newbee or even code by itself. This was a pipe dream from the beginning and some people/companies still sell it that way.

In the end AI is a tool that helps everyone to get better but the knowledge and creativity is still in the people not in the input files of chatgpt.

In my experience AI is wikipedia/stackoverflow on steroids when I need to know something about a field I dont know much about. It has nice explanations and you can ask for examples or scenarios and it will tell you what you didnt understand.

Only when you know about the basic notions in the field you want to work with AI can be productive. This is not only valid for coding but also for other fields in science and humanities.

Well it's not stackoverflow on steroids, otherwise it'd give you a surly "why do you want to do that?" response and then delete your question.

Man I don't miss that place or those people. Glad AI's basically destroyed it.

Except stackoverflow was only occasionally hallucinating entire libraries.

Perhaps asking the machine to do your job for you isn’t as effective asking the machine to help you think like a senior and find the information you need to do the job yourself.

When you ask it for information and it just makes it up (like I just described), how is that helping the senior?

I’ve literally asked for details about libraries I know exist by name, and had every llm I’ve tried (Claude, Gemini Pro, ChatGPT) just make shit up that sounded about right, but was actually just-wrong-enough-to-lead-me-on-a-useless-rabbit-hole-search.

At least most people on stackoverflow saying that kind of thing were somewhat obviously kind of dumb or didn’t know what they were doing.

Like function calls with wrong args (or spelled slightly differently), capitalization being wrong (but one of the ‘okay’ ways), wrong paths and includes.

I have been burned so many times asking LLMs about whether some tool/app/webapp has a feature, if so where I can find or enable or disable it, etc. The number of "just plausible enough to believe" hallucinations I've got back as answers is absolutely maddening.

I've lost count of how many times I've asked whether some command line tool has an option or config available for some niche case and ChatGPT or Gemini shouts "Yes! Absolutely! just use '--use-external-mode' to get the behavior you want, it's that simple!" and it's 100% hallucination created by mangling together my intent with a real option in the docs but which in reality does not actually exist nor has it ever existed. It's even worse with GUI/menu navigation questions I'm guessing because it's even less grounded by text-based docs and trivially easy to bullshit that an option is buried in Preferences, the External tab maybe, somewhere, probably.

The desperate personality tuning to please the user at all costs combined with LLMs inherently fuzzy averaging of reality produces negative value whenever I truly need a binary yes/no "Does X exist in Y or not?" answer to a technical question. Then I waste a bunch of time falling back to Google trying to definitively prove or disprove whether "--use-external-mode" is a real thing and sure enough, it's not.

It does occasionally lead to hilariously absurd exchanges where when challenged instead of admitting its mistake the LLM goes on to invent an elaborate entirely fabricated backstory about the implementation of the "--use-external-mode" command to explain why despite appearing to not exist, it actually does but due to conflicts with X and Y it isn't supported on my environment, etc, etc.

I use Claude Code, Roo Code, Codex and Gemini CLI constantly so I'm no kneejerk LLM hater to be clear. But for all the talk about being "a better version of Google" I have had so much of my time wasted by sending me down endless rabbit holes where I ignored my sneaking suspicion I was being lied to because the answer sounded just so plausibly perfect. I've had the most success by far as a code generation tool vs. a Google replacement.

>ChatGPT or Gemini shouts "Yes! Absolutely! just use '--use-external-mode' to get the behavior you want, it's that simple!" and it's 100% hallucination created by mangling together my intent with a real option in the docs but which in reality does not actually exist nor has it ever existed

Yeah I've had that one a lot. Or, it's a real option that exists in a different, but similar product, but not in this one.

If we're just back to I do the work and use a search engine, why futz with AI?

If the free market is any indication, because it’s more effective than what passes for a search engine these days.

It's not, but there's sure a lot of money and pride riding on getting people to believe it is

16.4 billion google searches per day vs 2.6 billion consumer chatgpt prompts and another 2.6 billion claude prompts. Maybe it’s apples and oranges but google has been a verb for nearly twenty years (oxford added it as a verb for web search in 2006).

As opposed to SO always somehow ending up giving an answer where boost or jQuery was the top answer.

I've been really caught out a few times when ChatGPT's knowledge is flawed. It gets a lot of stuff about DuckDB deeply wrong. Maybe it's just out of date, but it repeatedly claims that DuckDB doesn't enforce any constraints, for instance..

I agree, you need to know the "language" and the keywords of the topics that you want to work with. If you are a complete newcomer to a field then AI wont help you much. You have to tell the AI "assume I have A, B and C and now I want to do D" then it understands and tries to find a solution. It has a load of information stored but cannot make use of that information in a creative way.

Also AI cannot draw conclusions like "from A and B follows C". You really have to point its nose into the result that you want and then it finally understands. This is especially hard for juniors because they are just learning to see the big picture. For senior who already knows more or less what they want and needs only to work out the nitty gritty details this is much easier. I dont know where the claims come from that AI is PHD level. When it comes to reasoning it is more like a 5 year old.

Learning == Compression of information.

It can be a description by a shorter bit length. Think Shannon Entropy and the measure of information content. The information is still in the weights but it is reorganized and the reconstructed sentences (or lists of tokens) will not provide the same exact bits but the information is still there.

The compression is lossy.

How good can you recreate an image that is described by words? Obviously not bit by bit and pixel by pixel. You get something that resembles the original but not an exact copy.

you can create original exactly with right prompt

Yes. For example, you could always say "give me a jpeg image file that is encoded as the bytes 255, 216, 255, 224, 0, 16, 74, ...". But that's just pointing out that the input to your "LLM" function includes the prompt. It's f(model, prompt) = response.

It's not straightforward to prove that models have to be lossy. Sure, the training data is much larger than the model, but there is a huge amount of redundancy in the training data. You have to compare a hypothetically optimal compression of the training data to the size of the model to prove that it must be lossy. And yet, it's intuitively obvious that even the best lossless compression (measured in Kolmogorov complexity) of the training data is going to be vastly larger than the biggest models we have today.

You can always construct toy examples where this isn't the case. For example, you could just store all of the training data in your model, and train another part of the model to read it out. But that's not an LLM anymore. Similarly, you could make an LLM out of synthetic redundant data and it could achieve perfect recall. (Unless you're clever with how you generate it, though, any off the shelf compression algorithm is likely to produce something much much smaller.)

no, the simplest example that it is not possible in practice is in heraldry, where blazon - that is description, yield different emblazon - that is depiction, depending on who and where creates crest

crest always stays true to descriptions but details are always different

now when I think about it, heraldry is practical way to describe how generative algorithms work

It is at least as lossy as jpeg compression. Details get lost and artifacts are generated.

how long would it take to do a complete memory dump of your brain by voice stream? days? months? years?

this is more like writing one's autobiography.

There are some fun early theoretical ML papers on this topic.

They prove that it is possible to fully clone a brain based on this method.

I think one could theoretically estimate how many queries you would need to make to do it. The worst case is proportional to the number of parameters of the model, i.e. at least 10^15 for a human. At one minute per spoken sample, that comes out to about 2 billion years to clone one human.

I suspect it is not practical without advancements in neural link to increase the bandwidth by billions of times.

I personally like playing around with empirical methods like this blog post to understand the practical efficiency of our learning algorithms like back prop on transformers.

I also try not to invest too much effort into this topic given the ethical issues.

I was thinking about selective knowledge exploration to see if the candidate is fit for the offered position. No need to dump everything