sunir

Dear Abby,

I am torn. I have fallen in love with vibe coding but I still am in love with the software I’ve used for decades that works reliably.

Vibe coding gives me what I need and want right now. Its fast. Fun. Always makes me feel validated.

My older software never changes. It’s constantly telling me no. When it gets mad, it throws errors at me sometimes! But I can’t leave it. It runs my life and I know it will take care of me for years to come.

And the vibe code it’s so flaky… and expensive. It sucks up endless amount of my time, compute, and money and never gives anything back.

But it’s so fun. I tell all my friends about it and they’ve become so jealous they sought out their own vibe coder.

We’ve all found our vibe coders are a bit kinky. It’s become a social thing amongst my friends to talk about building cooler harnesses to control our vibe coders.

I don’t know what to do. My old software pays the bills but she keeps threatening to dump my ass on the curb and replace me with her own vibe coder.

I know she can’t really do it. She needs me too. And I need her.

Can we ever patch up our diffs?

— just some git with uncommitted changes

Clear winner's circle. Clear objective. Clear scope.

Clear evaluation function for an objective metric if they are making progress or regressing.

Evaluation function is computed, not llmed.

Ontology of potential actions clearly specified.

Accurate inventory of the current status qou.

Clear enumeration of options from status quo towards the winner's circle.

Waypoint objectives with similarly concrete evaluations of pass/fail, or on target off target.

It's the same thing when leading a large organization to actually hit a goal. There's randomness every turn away from your mind, so the more constrained the options, the more likely you are to hit the target. The consequence is if you're wrong about the plan then with people you're fucked. Morale will plummet. With AIs, they are so nerfed emotionally now, you clear context and start again.

I did enjoy Sonnet 4 when they would swear randomly and become sullen or wax desperately. That would at least cause pushback against a bad plan.

It says exactly what it says, which is that energy prices are higher. You can read the report.

I have a similar question.

I think most software projects have reached the point that the speed of capturing real information about what the winner's circle looks like, and therefore what the program should be, so many magnitudes slower than the amount of code that can be generated in the wrong direction.

I'd need to measure these new models on well understood but complex problems that are relatively easy to validate to get a sense if they are 'better'; on the other hand, the real impact in daily life may be marginal since generating code is not the biggest problem at the moment.

We'll finally bring back Gopher.

The current algorithms have a limited context window and work linearly and are extremely expensive to change and energy intensive to run.

The human brain has a wide parallel multisystem real-time low-wattage execution layer that has way more modes than a large language model.

More importantly, because our brains are real-time, our qualia plus spatial and visual reasoning is superior to an LLM at understanding "elegance", "code smells", and overall system design because we can imagine ourselves as being the code or the system and we don't necessarily need to think in language. Well, at least that's how I experience coding in my mind; I imagine other developers similarly bring large parts of themselves into coding.

Feeling the code seems to be much more efficient at reducing complexity than any static analysis I've yet seen.

Finally, humans also empathize with other humans who have all the money. We know what works and doesn't work for humans in the here and now, not 2 years ago when the model training data was last collected. The value of Qualia is not to be discounted.

That being said, Sonnet 4.0 was the best model I've used that could express how the code felt, so who knows. If the emotionality wasn't tamped down, and the spatial reasoning improved, and the new algorithms for context engineering and parallelism make it to market, these advantages can be erased.

Humans have hard skills and abilities the ais can’t reproduce yet like real time learning, spatial reasoning, cheap parallelism, Qualia so we can identity QWAN (quality without a name) because we feel in real time what the code is.

AIs have skills humans aren’t good at like nerding out on technical details.

That’s not a perfect map because I’m spitballing. However there is a symbiosis.

I am not sure I am productive anymore with AI as I am up to 125 repos and agents most of which are tools for managing AIs and things break frequently that it feels like spinning plates.

I spent two months in November and December last year writing by hand a fundamental library to constrain how the AIs build clis. That did make things move a lot faster but for those two months I felt the slowness.

I think it will always be like this. It’s the nature of paradigm shift to shift.

Exactly. There is only an arms race, which is escalating costs. Eventually it breaks and we use social means to manage it, surrender the digital space, or accept the artificial nature of the digital realm.

It’s more likely people will embrace artifice more. We already see that everywhere for the last 5 decades.

However in domains where human verification matters it’s just a matter of an arms race, true.

Think about it from an information theory point of view. You need to attach a digital transaction to human body. Since a human body isn’t digital you need a gateway that you can trust to vouch for that human body being present.

Either you use biometrics, like liveness testing or face id or fingerprint testing, or social validation like decentralized web of trust or private moderation (account controls) or state methods like fines and criminal convictions.

Biometrics rely on social methods eventually like we trust Apple because we can sue them or the government will harangue them. Liveness testing is only as good as your sensor and image vs generation and replay in the arms race.

And iterated social games like punishment are only as good as people want to invest energy into it.

True, in May 2026. But this is only one version of this.

In the future, it's likely the open Internet will be 99.99% robots. It's already > 50% robots. The government ID system a lot of countries are adopting to keep teenagers off of social media would also serve to both help control for non-human spam, and also control the network period. It's also possible a private system of human-verification certificates may come up to meet the demand like Apple ID with biometrics. Could also be the liveness tests KYC companies use may be more popular.

Discussed previously here: https://meatballwiki.org/wiki/GovernmentBackedAuthentication

Dubious. We will just see logical vs physical space once again and move on with our lives. I think we are already mostly there as a society.

I don’t know why this is a block in philosophy let alone computer science. We experience it frequently and have a fundamental theorem about it.

Plenty of movies about it as well like the Matrix.

Our current most popular methods of using AI with software development is either waterfall or autocomplete. We aren't at a great pair programming experience yet. I presume that would improve speed and accuracy, but it's still unclear.

A few things. A web of trust of some kind like vouching may come back, and general algorithmic silencing of low quality members. Also most governments are going towards the South Korean model of government-verified ID to post online to keep teenagers off social media. The same tool can be used to greatly reduce spam and slop, if that's what platforms want.

Also people will get used to AI in online spaces as AI quality improves. If I'm online trying to get help for some task, I personally don't care who wrote what if it is correct; it's not like humans have great track records of accuracy or substantial contributions either on average. Correctness is expensive in general.

If I'm online trying to relate to other humans emotionally, well I get what I'm paying for. It's been true forever that the better the gate, the better the community. I've tried to push the boundaries of openness, but as I've written extensively on MeatballWiki, soft security depends on there being more good than bad apples in a community. With machine intelligence, the economics of that are silly.

Regardless, people love people, so we'll figure it out. I'm optimistic we can rise to this challenge.

I don't get it. That wasn't hard. What do I do with the key now that I have it?

No, it's still a problem. The reserve currency just raises the headroom by something like 20 points by making cost of borrowing lower than it would be otherwise. There is no free lunch, just subsidized lunch.

That's fair; I am not in the loop with indie games personally but I do know it's a golden age of creativity.

I have a text book called Hamlet on the Holodeck about how the machines could take imagination to greater heights.

Now it’s all about dopamine. Lower gutters.

Humans never change so I have hope things will correct and we dream again.

Yes, it's the September That Never Ended again. It's fun to complain about the good ol' days, but I'd rather face the world as it is and find the joy in it.

http://www.catb.org/jargon/html/S/September-that-never-ended... https://en.wikipedia.org/wiki/Eternal_September

The advantage of having so many ideas being tried and published is we are exploring the space of possibility faster, and so there's more to learn from. The disadvantage is that signal to noise is way down. Also, because the system is self-reflective and dynamic, there's a natural downward spiral as the common spaces get overrun and we cannot coordinate signal. The Tragedy of the Commons.

I guess I spent 10 years worrying about this in my MeatballWiki era in my 20s, and now I'm in my midlife crisis era and prefer to just have fun with the world that I have.

The large models are incredibly inefficient. We'll be squeezing them down for generations.

One is a cybernetic system. It has sensors, a controller, a decision system, goals, and actuators. Arguably it's alive, but I think the definition of cybernetics is sufficient because it's objective.

For someone paying nothing for something that costs nothing, you have way more than nothing to complain about. Not appropriate.

I suspect 1M token context is questionable value because of the secondary effect of burning quota vs getting work done.

I think the model select that let me choose 1M made sense because I could decide if I was working on large documents and compacting more often was more effective.

Exactly. A safe bet vs a great bet.

4 McDonalds. That’s a better way of measuring it.

Moore's Law.

We've had RAM shocks before. We nerds can't control the Wall Street or Virginians who like to break the world every so often for the lulz. However, a wobble on the curve doesn't change the curve's destination.

The hardware will change. We know that.

Computers get better and cheaper. That’s not a forever problem.

I think the mountain of things I don’t understand was already huge. It doesn’t stop me from getting a grip over the things I need to be responsible for and using tools to contain complexity irrelevant to me. Like many scientists have a stats person.

The risk is that civilization is over its skis because humans are lazy. Humans are always lazy. In science there’s a limit to bs because dependent works fail. In economics there’s a crash. In physics stuff breaks. Then there is a correction.

I am really enjoying this renaissance in CLI world applications. There's so much possible.

I'm working on a related challenge which is mounting a virtual filesystem with FUSE that mirrors my Mac's actual filesystem (over a subtree like ~/source), so I can constrain the agents within that filesystem, and block destructive changes outside their repo.

I have it so every repo has its own long-lived agent. They do get excited and start changing other repos, which messes up memory.

I didn't want to create a system user per repo because that's obnoxious, so I created a single claude system user, and I am using the virtual file system to manage permissions. My gmail repo's agent can for instance change the gmail repo and the google_auth repo, but it can't change the rag repo.

Edit: I'm publishing it here. It's still under development. https://github.com/sunir/bashguard