acoye

Why do you think, is it lack of capital available in Europe ? Over regulation ? Simply a vision problem ?

"It's actually le gros chaton"

I hear you maybe my summary of the tool does give this impression.

Here are actual small use cases that work for me:

- Aggregate the markdown files of a git project in one place. I can version them, review them, dump them, search efficiently into them. Useful to me before launching long agentic tasks, I specify all I want to beforehand.

- "Cron" checks on new versions of libraries. This works without specific APIs or any setup. A document is maintained with the latest seen version in a specific path of the document base. I also had good results tracking new stars and user adding them with this.

- Press review / OSINT I built myself a "President Daily Brief" Same thing. It can "reason" given the old daily briefs and assess if the situation is worsening or not on a specific issue, and make basic forecasts. It tracked down the current Ebola crisis before it went mainstream for me and predicted correctly it would worsen.

I guess I use this for long term memory basically, where I keep ownership of long term knowledge locally. It's more a metaCerebralCortex, and openClaw "dreams" are the hippocampus coalescing these memories at night.

Also, please note each document in base has a virtual "path", so beyond tags and search you can pin down on a specific domain. It is structured as a tree.

I do understand that if I were to build a harness this would possibly not be a good fit for the core of it.

Does this make sense to you, or would you just basically do without such a thing at all to keep each agentic task context clean(er) ?

I recommend the manga BLAME! that explore what happens to humanity if you push this to 11 https://fr.wikipedia.org/wiki/BLAME!

I'd love to see John Carmack come back from his AGI hiatus and advance AI based rendering. This would be supper cool.

Nvidia CEO reckons your GPU will be replaced with AI in “5-10 years”. So this is what the sort of first working game I guess.

Yup that's a Teenage Engineering OP1 designed to look like a keyboard :D

I wonder if Swift's AsyncAwait could be used in such a way.

I quitted 8 years ago, banned in my personal DNS, never looked back.

I use private chat apps to replace it, and full disclosure I enjoy from time to time loosing some time on twitter.

INT-P speaking, this may be helping me.

I had this crazy idea a while back using Ray tracing APIs to piggy back a database. Testing for a row could be done shooting in parallel rays to a structure mapped to the data.

I knew it, “apple silicon” branding allows them to de-normalize ARM at will.

Neural net trained on data obtained with … computation. Or else Mr Wolfram wants to hear from you as you broke the `computational irreducibility`

Well in the philosophy problem space, ethics and morals are clearly a complex matter haha.

If someone’s ethics is to maximise chaos, then a full disclosure on 4chan is _technically_ the _most_ ethical action for this person.

Consider `life` been a nonlinear chaotic process, so causality from been smart alone cannot be established.

Creating a `complete` (in a mathematical sense) computing system.

Elements of Euclid ? You build the proofs in your head step by step.

Compressor, so we can have refrigeration and feed million of people safely between other things.

You would then have to try to ban bitcoin Why would an individual want to keep around an eroding by design currency?

> In addition fedcoin would traceable (anti crime)

You would only successfully trace the law abiding citizen IMO.

A strong cloud simulation is key here.

If morality is derived from a belief in God, then a nihilist could argue any form of morality is essentially artificial.

I feel it goes against the idea I (we) may have about personal freedom.

This makes someone not aware of said systems a puppet doesn't it? To the point you think you have freedom, but your attempts could be doomed to failure.

We are still free to shape our networks yes, and it requires work ... So success is a function of how good you are at Psyop then /s

I concur. I'm from "Savoie", FR Alps. I have filmed on Hi-8 the glaciers nearby where I lived as a kid. Some are just no longer visible from the valley.

You are correct. I was running low on caffeine . https://en.wikipedia.org/wiki/Fast_inverse_square_root

I kind of want to run Doom on this too : 167i-k Vi *QVk reciprocal square root approximation

Hey look, it had the NSA's magic instruction: 106ij0 Si PSj population count

Secret is out, everybody hangs out on twitter nowadays. https://www.youtube.com/watch?v=VCwiZ2dh17Q

Probably somewhere on the other side of the looking glass … I mean freenode.

Maybe "old school hacking" is still present in the "maker" movement. For the pragmatic, practical hands on approach I mean.

I was following the old GH issue / thread related to OpenCL support for 1.x of TensorFlow. I tinkered an got it working with opensource kernel drivers on GCN1 (HD 7970) https://github.com/tensorflow/tensorflow/issues/22

You could do it, and GCN was good at compute (still is with Radeon VI) but I must admit it was far more complicated than any AI researcher would have liked compared to the closed source binary approach of NVidia / Cuda.

I wonder if some day they will come up with another Snow Leopard. Or if the size of teams and the complexity of the product line is an inescapable doom pit.