sunir

I'd also like to reveal a Chapter 11 restructuring of Anthropic in 2029 to cancel these contracts.

I mean, I can't reveal that because I'm just some schmuck. But I'd like to.

I'm building a high level code explorer, like the CASE systems of a long time ago I suppose. I also built a facility called zork that lets me and an agent explore the code system together like a dungeon, taking notes as I go and if you want to take the metaphor too far, 'invoking spells' or rather commands like code references, call flow, data flow, exception flow, profiling, labelling design patterns and validating implementation, etc.

With zork I can also just start typing in a code file and leave instructions for the agent to fill in or fix parts of the code while I'm editing it. So I can lay out what I want the class shape to be and don't have to implement all the annoying little parts. This feels more like the GitHub Copilot days.

I honestly believe more of us will pair program with agents, not just yelling at a chat window.

I didn't say that. I just pointed out that computers are better at these mental activities than humans, and humans still do them. More in fact.

Academic mathematics isn't an operational institution.

Though its funding does move with the number of major projects academia is tasked with that rely on mathematics to advance, it's a fundamental knowledge area that has no operational requirements to exist.

People still play chess and go and StarCraft. People do what people want to do. It's not clear whether this will reduce the number of working mathematicians or increase it. There will a lot to learn from the machine proofs that will open up new frontiers as well.

So, it's like the story, "We'll see."

There has been a shocking but not altogether surprising development, and all reactions are valid.

sudo pmset disablesleep 1

Your Mac will now work while the lid is closed.

I predict we are less than 12 months away from the pendulum swinging back to hand coding but dragging ai pair programming into the workflow. This is why I don’t worry too much about this.

I can predict this because I’m building such a thing for myself as are many others. It seems to be where the tao of slop is going.

Here's a good set of questions for any write up:

Who are we talking about? What's their role? (What agent? What is the job to be done?)

What is the status quo? What's the problem with the status quo? What else has been tried? What's the consequence of not solving the problem? What more important problem do you need to work on that you're blocked because of this problem? What's the ideal solution? What's the current offer? Why would someone say no to any given solution? How have you addressed those problems?

When I was younger, I was in Berlin and wandered unannounced into the Chaos Computer Club and I met Tim there. What a legend.

The whole club is legendary. We need more of their spirit of the art of the possible and irreverent. Life is for the living, and computers are for the hackers.

Yes. I have so many stats texts and like many technical fields I suspect they are written as if we learn how things were derived historically not how they truly are.

It’s more likely that they have llms supervising llms in training and therefore the quality has dropped like a picture of a photograph.

If opus has high signal thinking it would be able to write a fsm but it’s been a month of me trying whereas Luna can do it in a few minutes.

I think it is similarly that they are using too much synthetic data.. meaning they are feeding the models the transcripts of users where many users have figured out to let agents just message each other.

Again picture of a photograph.

I'm still traumatized from Space Quest I because I didn't grab a broken glass from the windshield of our crashed spaceship before entering the cave with the laser.

It's been 40 years. I vote wkfauna for President.

I'm sorry you're getting the lash end of the whip. The rage against the (literal) machine is very high right now. I appreciate you sharing your creativity, and frankly, I am taking notes on what you've built for a related but different project.

Don't forget Hacker News is known for amazing commentary like this https://news.ycombinator.com/item?id=9224

From a computer science point of view, it's the same argument as why NP-complete problems are hard to solve, and easy to check.

From a practical point of view, however, it's the same argument we write unit and integration tests. We accept error rates in the program under test, the test, the test harness, the programming language, the operating system, the hardware, and the universe. The goal is reduce the error rates enough you can ship something you can get paid for and won't get sued for later before you starve to death.

Try the left arrow in Claude Code and now you have session search. Or claude --resume, down arrow, then Ctrl-A to see everything

you can name Claude sessions using /rename. also tmux is your friend.

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.

I’d like to remind folks every expert system already knows how the AI hype train always goes.

It’s not a normal tech adoption curve because AI is not an extension of ourselves like a shovel extends our hands or a car our legs. AI hits deep human instincts about what power means and also our antagonism to other hominids.

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.