metchio

sometimes humans do irrational things / have illogical behaviour just to glorify their own ego. it happens also to the very best sometimes

who doesn't need to merge and compress bunch of pdfs on a friend phone on a saturday morning

thanks for the great comment! You answer is great too, I will probably think about it for the next 4 nights or more, triggering my wife's comment "why are you so weird and distant? are you cheating on me?"

generally i expect if i invoke `touch file` to see my file update date as now, on the filesystem. so i want to have a mapping between physical world (in this case, memory on my machine) and intelligence representation. If the LLM terminal, upon invoking `touch file` does not update the physical file, it is not a real terminal. you can argue that i will use the terminal itself to invoke `ls -la` and check the updated file, but verifying from an external scope is mandatory imho otherwise it's obvious you cannot logically demonstrate that. hope i was clear

i agree absolutely with you. and this kind of reinforce my idea that, like this predicted terminal could not be considered a real terminal, predicted intelligence could not be considered real intelligence

fair enough. I didn't want to look aggressive, sorry about that.

wait until they found like 90% of the chinese model hosted on huggin face have some sort of backdoor/secret phrase activated spy mode

I don't understand the point of this article. It is written poorly. It doesn't state a purpose or line of thought, you can infer it from how he counters the dislike reasons, but then was the point of the article just to list a handful of reasons you don't believe to be true? Because he's leaving so much stuff behind

it's a wrapper around a model that actually executes commands from text input. Claude Code is an harness : the underlying model is Claude (with the version of your choice), Claude produce text output like `grep -in "error" server.log` , Claude Code actually execute the code in your shell and return the output to the model

I made a simple gif of Anthropic logo transforming into Umbrella Corporation logo. Everyone in the office laughed

I just want someone to put the same concepts and ideas of Windows Phone OS (Lumia era) into desktop computer. That's all I desire. A beautiful type-oriented experience. I feels like with the rise of LLMs and Agents could be even bigger than 20 years ago

there's no button on the glasses to turn the Bluetooth on or off, so they're basically always connecting as long as they are powered.

this is amazing. really awesome

and somehow, all of this researchers warning us about the AI doomsday, are only been active online for less than a year. This guy created the Twitter account on January this year. I never see any of these posts coming out from a well known community active person

I agree this is so nice! Would be awesome if some variation of this becomes the norm in every big city or turistic landmark. It's relatively cheap for local gov to set and maintain couple of those and brings back a different way of using the technology/interacting with people.