I don't see the relationship between "fun and learning" and "(beyond) impractical".
I enter most of my learning project from the assumption that I could just buy/install whatever I am building and save time/money.
Please consider seeing things from a different perspective than "your book".
Not saying this to antagonise you, but because a lot of time reading comments like this makes other posters less willing to share their impractical efforts, and would love to read more of those, not less.
in a container a daemon is managing the telnet connection/logins and throws into a parser, that takes grammaries (basically, lists of regexes) and produces events, which are appended into simple files as json blobs (with types: rooms, npc enters/exists, unknown, etc)
agents can tail live logs or parse in any sense: i built agents that try to classify (via grammar file edits) "what that unknown event is", build experiments and verify against live runs
surprisingly, a local 27b is quite smart
ultimately you need to run fast inference for combats (5 second rounds), for that i built a system to prepare fine-tuning runs over 3b models
overall, using container primitives for everything seems to be the biggest gain: in the end they mostly are coding models, so intuitively know how to interact without needing too many explanations
example: mud commands are small bash commands, the "game help" is provided via man for those commands, and hence when there are attempts at reasoning (which is done for knowledge building via grammar files) agents are great at using apropos to find out more about a specific topic
another example: setting a "pick all money from body" is a tail + grep, once the agent is shown it he picked up usage quite fast
to run agents i use pi and simple setup where a main 27b agent acts as an orchestrator and delegates runs to agents (orchestrator also build prompts), usually as "experiments" "if i classify event x than what should happen in-game"?
i do not really keep it running all time, it's mostly about me putting up challenges, see what happens, and using that
as a learning experience
I am having a hell of a lot of fun letting agents play and understand a (still alive, human populated) MUD, which I have also played for the last 30 years.
It’s mostly my way to play with local llm inference (m5 64gb, gwen3.6 27).
It’s amazing. They build maps, classify events (building a grammar for a parser), run experiments (to verify the grammar).
They are now (given the correct tools/infrastructure) trying to fine-train a 3b model for fighting (where you need a decision for 5 seconds rounds). Basically autonomously!
Overall, a MUD does prove a great constrained sandbox for them to play in.
What started as an experiment to test local inference landed in a sweet spot for seeing models strength/weaknesses/tradeoffs. And it’s really fun.
Only problem is that Claude gets really jealous when I ask him to code their po harness running local inference. Weird world.
> There is a part of me that wonders if it's partly just how much they can hold in their head right now, though. Even with the greatest articulation and high density of feeding them, the current setups don't allow them to hold a high-quality, sparse, 'zoomable' model of the world in their head that well yet, which we can do pretty well.
My personal experiments show that giving them tools to access to all past sessions over a codebase helps a lot. When I coded "feature X" 2 months ago i likely specifically mentioned some constraints expressed as abstractions and, if the coding agent checks not only the code/feature it needs to implement/change but also the past sessions over that, it picks them up, and ships code that better fits the overall project.
At least, more than "architectural/design guidelines", since they are more "concrete", to the point for the task at hand.
Sessions self-preserve them for following sessions, which helps, but might also carry over stale things, so some "pruning" helps, and can be automated. Overall, as long as corrections were also made via agents and hence in sessions, they are picked up automatically.
It's not the "human zoom" you refer to, which as humans we can drive/control, but the effect seems to be similar: I read autonomous sessions where it picked up from the past the very design/architecture/abstraction points i would have driven, had I been in the loop.
In team contexts it should not be impossible to share sessions, but I not working in teams right now :D
So maybe it's also a "single dev quirk".
Another point is that in a sense, learning to code goes from being told "you are using the_wrong_abstraction/this_abstraction_the_wrong_way/no_abstraction_where_you_should_have", to telling it to others/ourselves.
Since the number of knowable abstractions seems to be "at least one more than I already know", agents can actually be helpful in learning.
After a certain threshold, it basically zeros in a specific domain, but on novel domains agents taught me abstractions, when nudged towards doing that.
OTOH all my attempts of driving harnesses via chat have been frustrating because they all fail against the fact that I want to see the code and mobile devices are not really good at that.
Better on tablets, but even there I get more value on having final html artifacts pushed on a server and inspecting them, and dashboards.
Is there some obvious use case I am missing? Or tool for inspecting code?
I don’t run openclaw et al, is that a context where you find this valuable?
i agree with your point: "we" always wrote code and abandoned it
the claim here is made against flatpak submissions, which involve pr reviews
i think a point being missed is that open source has always written code that was going to be reused by corps, but PRs in it were likely to help humans join open source, and develop coding skills
As someone belonging to the group you just described, I like discovering things from first principles, and build them.
It’s a big part of how I get to learn things, and find it fun.
This thread is helping me see how others addressed the same ideas.
I get and share criticism in the context of “AI hype startup culture”.
But out of it, this thread is really valuable for me mostly because of the links to codebases.
“Siloed individualistic development” openly shared is the part of HN I like most.
local LLMs builds tool that does exactly what user wants, how it wants it, which is bext UX
this becomes AI literacy
LLMs already nicely bridge the gap form "I want this" to "here's a local page that does it".
examples of tools i have built that requires almost very low tech knowledge
* push a button on my phone to take screenshot in my mac (when i watch videos)
* help me exercise, gamify it for me
* "help me track time spent online to how it impacts what i do in real life, built a tool that rewards and me points me towads things that make me DO things online"
* i want to improve my writing, give me exercises and build addiitonal tools (leading to an "append only" digital keyboard i use to exercise )
local AI can already create these tools, and no external company is ever going to beat me/the-user because instead of getting features i don't want, or that almost do what i want, or that do something that advantages the company they just do what I want
Repositories of tools-as-ideas created by others are quite often just index.html and ... that's all? manage data in localstorage, end of it?
Online inferences is still needed for large data (audio/video/images) processing. For now? we don't know, history suggests we'll have the capabilities to do that locally "soon". Or maybe not :)
The main issue is "online for collaboration". Not same user across different devices, that is easy.
MeteorJS-style approaches (making local copies of part of dbs, reconcile to remote/origin) seems to be an interesting possibility at small scale, since once you have the right primitives in place you can go horizontally everywhere.
Commoditizing complements.
If Anthropic/OpenAI/etc is eating your lunch, make it work with cheap local LLMs , you can beat them on price by having local inference you don't pay (nor need data centers for), and try to keep your (user/data) moat.
The more Anth/OAI disrupt, the more likely this is to happen. If they don't disrupt enough (.ie: grow as an ecosystem to defend against incentives to commoditize), then yes, those incentives are removed, but they also leave money on the table, which they need.
Not only at business level, but also geopolitical (to a lesser extent? or not since lots of open weight models comes form China?).
> Some things are too important to violate just because 60% of people are afraid.
We need to avoid this becoming "60% of people should be stopped because 40% disagrees with them".
Alas, constitutions have the purpose of defending core values.
Separation of powers lets judges strike down gov bills and laws.
We have check and balances.
Diverging from them as an emergency measure for the "right" reason only makes it exploitable after the next election, if parties swap.
Instead of jumping from project to project, I focus on one (maybe a few) and let myself free while agents spew out their output.
Something physical is excellent for me: minor wood carving, origami, drawing exercises, also light physical exercises.
My trick is to (try to) do something that requires high focus, on unrelated matters.
To give a practical example, the simple gesture to connect 2 points on a sheet of paper via a direct, non trembling line, requires high focus: if you try to do it sloppily it is too long, too short, etc. I need to shadow the moment, gain focus, draw the line.
It keeps my brain in focus, busy and engaged.
Videos, podcasts, and in general enything digital seems to distract me away and/or overloads me.
Also, I am back at using pomodoro technique more frequently.
Just some pointers, in case you want to try out, or suggest some you find effective yourself.
Some traits I recognized in many excellent coders i worked with, their drive to optimization, intellectual thirst, critical and creative thinking are attributes i consistently correlated with them being in some sort of neurodivergence spectrum.
Being able to remove the "first step" block is great, but what worries me is that this is coupled with LLMs sycophantic behaviours.
My gut feeling is that coupling the feeling of unblocking ones capabilities with dopamine hits with the constant praising over someone abilities is an intro to psychosis and paranoia for them.
I think fundamentally we disagree on 1 principle, that "better" is the enemy of "good".
This leads to choosing which tradeoffs to accept.
And we are on the same side, to be clear. I want privacy. I also see what you mention, I just frame it differently.
Android being locked down is the worst case scenario: private companies makes rules, an update is pushed, no platform for discourse.
It's also the standard business practice when you let companies implement solutions to "privacy problems": put some privacy preserving lipstick on a fredeom restricting measure.... Specifically: we (google et al) need to verify apps so that we don't let them to do bad things to you, like stealing your data and ... sell it in the very same predatory data ecosystem that we have built and that we sustain for profit.
On the other hand, the EU sees that a law has been mocked on the internet since day zero (you must be of legal age to watch porn), in due time (30 years?) this has an impact on society, and shit needs to happen because yes, this is how laws work sometimes: they limit freedoms.
They have learnt from GDPR that delegating the implementation of laws to businesses is bad: they defang it and/or twist it so that the concrete result fits business needs rather than the principles established by law (as per above example: gdpr, ads).
So, the EU finds its own tech solution, puts down privacy as a core value, ships down a EU wallet and says "this is the reference implementation".
I like this! It's not "perfect", but i prefer this 1000 times over "let Google verify my age".
It seems to me that the EU has done an excellent job: now that society (including actors in bad faith) is saying "we need to protect the kids", we can say yeah ok, here is the good way to do it. They actually thought about this years ago.
Now THIS SPECIFIC document is .... ok!!! Because it is NOT to be read in isolation, but within the context (my framing) of EU actually giving me laws and tools protecting me. Over decades. And I have seen plenty of attempts at breaking those, and plenty of EU votes bouncing back those attemps.
Overall, there are 2 possibilities (aka tradeoffs on better vs good) when freedoms are attacked.
One (yours, as a understand it) is to say "this (VPNs, e2e, ...) is outside of the Overton window, just bringing this up is unacceptable/fascist".
You have good reason to defend this approach, and it's ALSO thanks to you and other activists (hope this does not mischaracterize you) denouncing and rallying around these issues, shouting "fascists", that we got them revoked.
The other one (mine? maybe?) is to craft a response that exposes the faults at play, naming and shaming business interests trying to hijack age verification to provide them with business advantages (example in this case: internet in Spain "stops working" when there's a La Liga game, etc, I'm sure you know what i'm talking about).
The willingness to rebuke these attacks in debates can be a slippery slope (opening the window). And yet, in present times politicians wear "being shouted 'fascist' at" as a badge of honour and they manage to translate that into votes.
There is a correlation that I see between "good" (argumentative discussing to convince) and "better" ("this is just not going to happen and we should not even discuss this because we have no room for fascism here").
Both are valid, going back to the beginnning we disagree on which to employ in this specific case.
All the above is about "framing", meaning a meta-answer over discourse. Also, let me be clear that I am not seeing you, or activists in general, as "mob shouting" by conflating that with lack of critical thinking, or ability to expose that.
I have recognized that your position has value, but let me be clear on that :D
Now to tech details.
Locking down network is impossible as long as decentralization is possible. You ban VPNs? People start using TOR.
They don't know and care, but in order to watch porn or sports, now they have better privacy protection across many other dimensions.
To gain usage, interfaces becomes simpler.
VPNs went from being a business tool to being a consumer tool precisely because companies started enforcing arbitrary rules. In order to get there you need to be easy to use, which makes their usage explodes, etc.
Constraints, scarcity, or urgent needs drive innovation, so i don not see autoritative pushes vs tech-for-freedom as a zero sum game (probably an even better description of why we disagree?).
Since businesses belong to the fabric of society, sometimes business rules goes into laws.
And sometimes whatever a government thinks is ok goes down there, principles be damned.
And yes occasionaly you get the guy that needs to go to jail, Prometheus-style. Clearly, Zimmermann. Arguably, Snowden. Provocatively, Kim DotCom.
So yes, banning VPNs is bad, but isn't it true that we have this problem because everyone can just flip on a VPN at any given moment?
Is this not a manifestation of a right that we have "acquired", in some sense?
In this context the EU has done, and is still doing the "good" thing: the EU wallet has not been assigned a budget and shipped over for development to Accenture or Oracle or any other private business. It has been given to open source researchers, and it leverages lessons learnt while building decentralized solutions.
While "everyone" was busy scamming users with ICOs, the EU has taken an interest on Zero Knowledge Proofs.
And EU bureaucrats have talked to nerds to understand if there is a way to have age verification and preserve privacy and make all the things that me (and you want).
Because, EU has been a global pioneer in elevating data protection to constitutional/human-rights status. Data protection worldwide, in the past decades, rests on me and you worrying and "fighting between each others", but mostly on the EU listening to us and being a global pioneer in elevating data privacy to constitutional/human-rights status, via Article 8.
To flip you statement:
the outcome of this is not the worst case of a single measure - the outcome in many cases will be the combination of measures taken by most forward looking governments across the globe that each protect certain freedoms.
sorry for the wall of text, i hope it was worth your time
Stopped midway through reading it to clarify something.
I don’t want your conversations :)
Anthropic has it and this is beyond me.
My plugin commits to your repo.
When it comes to keeping the WTF DUDE out of conversations, LFS gives you a net trick.
You can edit LFS blobs independently from git repo (different storage), so up to some point you can independently edit them out without touching git history (with caveats, it’s a rabbit hole).
Also, I think the inflection point is making it public. Git helps, just “fork” the repo without LFS to publish code only, or with a “sanitized” LFS (it just needs a touch of tooling to play with it).
I am also shipping a hook that sanitizes secrets by default (because security) and can be used also for keeping parts of the conversations… “tidy”.
I have built the “cleanup swearing feature”. Yes sorry it’s llm-turtles all the way down if you want automated, and extra cruft. But is also ok?!? I have a concern, I want to address it, I need to put some extra work…
I just want to clarify that privacy is my concern too and I have found that it’s not impossible.
I did not started coding until I found out that there is a way to contribute to a repo without participating in the “sharing conversations” game. (Not difficult: it’s your machine)
I am not publishing the repo until I have had enough conversations like this to introduce different opinions in my line of thought, especially around non technical hurdles.
My biggest concern is “why the hell would I teach an LLM that much of me, knowing very well this is how I will automate myself away”.
But even then, it’s either anthropic doing it, or me (coder, not plugin owner) AND anthropic doing it.
I am not advocating to giving away my skills for free.
One feasible variation of this whole record conversation is “commit code to company repo, commit reasoning to MY lfs”.
Why not? It’s my critical reasoning!!!
I enter most of my learning project from the assumption that I could just buy/install whatever I am building and save time/money.
Please consider seeing things from a different perspective than "your book".
Not saying this to antagonise you, but because a lot of time reading comments like this makes other posters less willing to share their impractical efforts, and would love to read more of those, not less.