pakl
Joined 14 years ago
Karma
221
Submissions
84
Member since
Mar 25
Recent submissions
Comment · 11 days ago
For “Germany”, the Spaniards say Alemania, the French say l’Allemagne and Arabic goes along with ألمانيا
Comment · 14 days ago
LLMs have shown a way to absorb large amounts of textual training data and be useful. For sensory processing you need a different architecture to absorb spatio-temporal streams. Bolting vision onto language models is stretching the tech a bit too thin.
The good news is the data is plentiful — it is all around (the robot). The real world — the robot’s umwelt sensed through its sensors and acted on by its actuators — will provide heaps of data.
Interestingly my colleagues propose that embodied learning will lead to grounding, alignment, and AI safety.
(Worked for 4 years at a robotics + machine learning startup, Director of R&D.)
Comment · 3 months ago
So many tools and libraries combine authorization and authentication, and it’s hard to find an authorization server that lets you outsource identity.
(All too often the underspecified abbreviation “auth” is used to cover both.)
Shameless plug: My colleagues and I implemented a minimal authorization server that lets you leverage a trusted identity provider of your choice (like Entra ID or even Auth0/Okta) and handle authorization. It looks up what roles and permissions the identified user should be able to have/grant and issues tokens containing that authorization.
Comment · 4 months ago
HTMs were a great theory but I never saw them function at more than 1 layer of hierarchy. So the “H” part was lacking.
Anyway since we know that any part of neocortex can be reached from any other within 3 hops, and there is more feedback connectivity than feedforward connectivity in nearly every part of neocortex, it should be called a heterarchy.
Hierarchy is a handy metaphor/mental crutch from understanding primate social organization, not necessarily how the brain works.
Comment · 4 months ago
There are ample known facts and published theories about neuroscience that have never brought together into a coherent framework. Everyone has their pet theories and focuses just on them in isolation. Let me know when some funder is genuinely interested in putting all the pieces together instead of grandstanding on a single idea.
Comment · 1 year ago
A few years ago Peterpaul developed a lightweight object-oriented system on top of C that was really pleasant to use[0].
No need to pass in the object explicitly, etc.
Doesn't have the greatest documentation, but has a full test suite (e.g., [1][2]).
[0] https://github.com/peterpaul/co2
[1] https://github.com/peterpaul/co2/blob/master/carbon/test/pas...
[2] https://github.com/peterpaul/co2/blob/master/carbon/test/pas...
Comment · 1 year ago
In most B2B cases you really don’t want to self host authentication. Really.
There are plenty of identity providers out there who will worry about hashing passwords, resetting them, 2FA, etc. Most client businesses already have identities via one of those for all their employees (read: users of your APIs or apps).
Unfortunately nearly all of the open source solutions out there do exactly what you said, they start with (required) self-hosting authentication. Not helpful.
What’s more relevant to businesses is authorization using existing IdPs (shameless plug: https://github.com/DMGT-TECH/the-usher-server)
Comment · 2 years ago
See “call-by-meaning”:
http://www.vpri.org/pdf/tr2014003_callbymeaning.pdf
Comment · 2 years ago
Think about it. A “meaning” in this usage is definitely not a longer name.
Comment · 2 years ago
IMHO (from the viewpoint of a neuroscientist) the biological inspiration is quite measured and restrained in his work…
The problem he was proposing we solve is computing with heterogenous “machines”. This doesn’t preclude the regimented organization you are favoring, above.
Please see my other comment on call-by-meaning.
Comment · 2 years ago
Actors solves a very different problem. Alan Kay was talking about enabling computing across heterogeneous systems.
Comment · 2 years ago
At Alan Kay’s Viewpoints Research Institute, the problem was phrased in a more concrete form and a solution was provided — “Call by Meaning”[0].
The most succinct way I have found to state the problem is: “For example, getting the length of a string object varies significantly from one language to another... size(), count, strlen(), len(), .length, .length(), etc. How can one communicate with a computer -- or how can two computers communicate with each other -- at scale, without a common language?” [1]
The call-by-meaning solution is to refer to functions (processes, etc) not by their name, but by what they do. VPRI provided an example implementation in JavaScript[0]. I re-implemented this -- a bit more cleanly, IMHO -- in Objective C[1].
[0] http://www.vpri.org/pdf/tr2014003_callbymeaning.pdf
[1] https://github.com/plaurent/call-by-meaning-objc?tab=readme-...
Comment · 2 years ago
There exists the Universal (Function) Approximation Theorem for neural networks — which states that they can represent/encode any function to a desired level of accuracy[0].
However there does not exist a theorem stating that those approximations can be learned (or how).
[0] https://en.m.wikipedia.org/wiki/Universal_approximation_theo...
Comment · 3 years ago
If you think about it, for embodied agents symbol grounding isn’t really the “problem”.
Rather, embodied agents start with reference and indices. The hard problem is actually ungrounding — which takes work — to eventually get to things that approach what people typically think of “symbols”.
Comment · 3 years ago
In an anthropological framework, social capital can be built up and exchanged for other forms of capital (including economic capital). There are even brokers who have the role of facilitating these transactions[0].
[0] https://bertrandlaurent.substack.com/p/monday-converting-soc...
plaurent at me.com or gmail
https://pakl.net