While the doc generator is a useful example app, the really interesting part is how you used Cursor to start a PocketFlow design doc for you, then you fine-tuned the details of the design doc to describe the PocketFlow execution graph and utilities you wanted the design of the doc-generator to follow…and then you used used Cursor to generate all the code for the doc-generator application.
This really shows off that the simple node graph, shared storage and utilities patterns you have defined in your PocketFlow framework are useful for helping the AI translate your documented design into (mostly) working code.
Bruno has been taking root in our organization (displacing postman).
It was nice to find out about the for-pay golden edition in this thread to support Bruno’s efforts. The feature split for free vs Individuals vs Organizations seems well done.
As feedback to the Bruno team:
for Individuals - I most value the gRPC/websocket, then load-testing
for Organizations - My org would most value central license mgmt
I think this is much more than an optical breadboard. The trick with the periscope is IMHO neat and allows for clean separation of the user's experiment from the invariant photon generator/detector part. Turning on the guide beam with a touch of a button is magic to anyone who had to labor on an optical table.
This might allow for set-up, alignment and conduction of an experiment within the short time allotted in educational settings, which would be quite a challenge using less smart constituents.
Maybe it's better to think of it as a team product. That being said, I'm sure there are people who could build something like that on their own by combining the right classes in a good engineering school.
Some raw feedback: It’s impossible to read on my iPhone. All content ends up in the far left quarter-column of my screen. I can’t zoom to see the content in that column (a default behavior for most sites). Switching to “reader” mode (to remove all the stying tricks) seems to show content that is not related to the article I was trying to read. I’ve rarely seen a site wreck an iPhone safari browser that badly :) - I’m interested in the topic though, so will try to remember to look when at a full-size browser.
Yeah, guilty as charged, and not acceptable. I don't yet know how to interact with the reader mode, but there's my weekend now. Thanks for the advance feedback and I hope you remember to check back as well :-)
Are there any examples of "Hello World!" with simulated basic brain cells? I'm sure this is an entirely naive question given the complexity of a brain, but I'm imagining a rudimentary program to help understand brain-style processing with some kind of brain cell struct unit that represents real-ish input/output mechanisms that can be connected to other brain cell struct units...leading to some minimal brain-style processing outcomes.
About simulation: we do have simulators of brains (to some extent). The main example is the simulation of the C. Elegans. One such simulator is on GitHub at https://github.com/Flowx08/Celegans-simulation
The problem is, well before tackling the human brain - with functional units, wiring, evolutionary rewiring¹, modules, multiform glias and mysteries in general etc. - that of transparency, i.e. already in the C. Elegans you can see complex behaviour in the studied system, but the hard part, that of understanding why and how that structure presents that behaviour, is unachieved. It is still a "black box" like some ANNs. We know the structure of the C. Elegans since 1985, but we still do not know well "why it works, why it works that way": the "scientific problem" of understanding the "natural phenomenon" we found, in order to export that understanding, is still pending.
So: we have simple brains described, they are simulated, and to just look at them will not make you much wiser until you really manage to "crack the code". There is not really an «Hello World» yet. It does not mean your doctoral efforts could not achieve it though!
--
¹ Evolutionary rewiring: the human nervous system is also made by "afterthought" increases which overlapped on pre-existing structures "patching" them, instead of "correcting, reprogramming" them - so one will find a system that may show to be a masterpiece of cleverness but not a masterpiece of planning. In other words, the human brain is something relatively messy, not a clean blueprint.
This feels easily related to lack of unified physical theories.
We seem to find structure all over but no idea why it ended up just this way.
My guess is a link between field effects and information coming off cells. Cells emit information instigating a field reaction but only to a certain point as a survival mechanism.
Once an equilibrium is reached the cells radiate new information to inhibit the field effect?
Which makes me wonder if cells not being able to inhibit field effects is related to aging.
I picked the wrong field in college. Math was fun but the kind of abstract that almost feels useless a lot of the time, and biotech really feels like the final frontier anymore.
I think you vastly overestimate our current understanding of the brain/neuronal processing, even singular (neuron) cell's workings. The fMRI enthusiasm turned out wrong a long time ago and there hasn't been much progress since, for all I know. And knowing a gene sequence wasn't enough either. We are still lacking theory big time. For most all of biology, we do not understand anything fully really. Not in neuro science, not in evolution theory, and god forbid not in genetics. Complex != complicated. Complexity is a hard barrier. We do not have abstraction for emergence, merely still recording thing's reactions when you poke them in different ways.
Do we even understand how DNA replication works? It's a relatively simple mechanical process, but it's performed by molecular mechanisms that exhibit oddly intelligent behavior.
The Human Brain Project is a somewhat failed experiment to understand the brain in its entirety. They started by taking human brain cross sections and imaging them down to neuronal resolution, but the scans took up so much space that there wouldn't be enough capacity on the entire planet to store a complete human brain scan. This is a challenge of compression inasmuch as it is a challenge of understanding brains.
I question if progress in any given field X is completely and unequivocally hindered by progress in a dependent field Y. If this is the case, dependencies better be known up front before embarking on any project, unless you like wasting time and money.
Ray Kurzweil presents one theory about the basic neuronal modules in How to Create a Mind (2012). The text is of course controversial - criticism may be as important as the tentative idea presented.
If you want to understand how the brain works this is a good intro with some realistic neuronal network models ( spoiler: these have nothing to do with “artificial neural nets” as we know them) https://www.amazon.com/Brain-Computations-Edmund-T-Rolls/dp/...
What an ambitious vision! This is a really neat concept and a great breakdown of the interesting challenges with making a great text-based experience for game users.
My kid was interested in starting with game programming a few years ago and I tried to push him down the path of a text adventure to start simple... and I recall not being happy with the text game engines I stumbled upon.
Here are some links I tracked down to play with it more:
Edit/Update: Contrasting the game on my phone with the how it plays in the terminal, while looking at the source files is blowing my mind :). The phone game rendering is really slick/polished -- I can see this was a labor of love. Nicely done.
The flexible WYSIWYG editing is top-notch! I’m sure you’ll get a thousand feedback ideas, but... if a next goal was to get folks to make it an expression/view of themselves, it would be good to help them connect content that they are already making back into their page. Being able to drop in a API feed of their tweets, blog posts or videos — and then applying some of your kitschy formatting to it — might bring back even more of that MySpace feel...
