EastLondonCoder

There’s a few things on this. I’ve read the trilogy many many times during my life. Every reread I found something new, something I hadn’t considered before. Still it was eerie to see Peter Jackson’s rendition because it was very close to how I picture the book in my mind.

So, I think if you know just a little bit of film making and writing and LLMs you know you could not prompt any of them into existence with just saying ”write lord of the rings”

But if you have an idea for a creative project, using an LLM to explore ideas can definitely be a fruitful endeavour.

The gods don’t give gifts by ghost goblins cannot be dismissed as slop. I’ve personally used LLM to explore large sets of photographs to use as a backdrop for a DJ set, essentially to have the set tell a story.

So, as most things, it’s complicated. But at the same time I’m curious what will happen next

I believe many of us here knows that the idea of a simple prompt to make something more than a sketch or a prototype don’t really work.

Unless you steer and understand what an LLM will produce, you will end up with something that possible ”works” that has no future plans baked in. Suno generated music has a very unpleasant feeling of sounding like competent music with nothing to say.

I’d say that vibecoded software is similar. My speculation is that current breed of LLMs do not have an I, and I really don’t exactly knows what goes on in those vast arrays of numbers. There’s something there perhaps, but no person.

Still even in the short term someone wants to run a company that expects responsibility of its organisation, how are you going to exact that responsibility if no one actually understands how the thing the organisation makes works.

Maybe a simple crud system can be made fast and loose. But a bank settlement? A pacemaker? Deletion of sensitive data?

I know some companies are betting on that the agent can fix what the agent breaks. It may be true, but up until now everytime I try to relax on strict steering of an agent it tends to go badly rather fast.

Again I don’t know, but I think as long as we don’t invent synthetic persons with their own ideas on what they want to do, which btw opens a massive can of worms, the current situation will persist. However clever the current breeds of systems are.

I do want to state that a find the current trajectory fascinating. I use LLMs daily, it expands the number solutions I can explore. But in order to make something I feel is mine. There’s a choice and the buck stops with me.

I can’t, and it’s not really the point. The point is that I got exposed to a new way of looking at a phenomenon that I haven’t thought about before.

For me it was a few years ago. I had seen a twitter comment referencing astrology in a spat with two black female musicians in the US. My preconception was to look up why that kind of superstition was prevalent in those circles.

The answer I got from chapgpt was essentially that it has very little to do with superstition and all to do with being able to use a language to talk about stuff while still not move outside cultural norms. More sort of a secret language where you can probe questions like if your boyfriend is violent, or if your friend is having an affair.

I think last year I saw some research on how the reading of tea leaves originated in the ottoman empire, it was remarkably similar. The point is that I learned something new that would have been extraordinarily hard to google, or even understand without putting some serious study into the subject.

I think the really dangerous part here is not just “surveillance bad”.

It is that AI removes the labour cost that used to limit surveillance.

CCTV was already a problem, but someone still had to watch it, search it, interpret it, escalate it. AI changes that. It makes surveillance searchable, scalable and administratively useful. The shift is from “you may be observed” to “your behaviour can be continuously machine-interpreted”.

That changes the moral shape of the state.

A democracy can have police, courts, borders, audits, fraud detection, and public order. I don’t think the serious argument is that no one should ever be watched. The question is asymmetry.

A free society cannot survive if ordinary citizens become more transparent to the state and its contractors than the state is to them.

The principle should be:

privacy for persons, transparency for power.

Police bodycams should make police accountable. Procurement should be inspectable. Algorithmic decisions should have audit trails. Whistleblowers and journalists should be protected. Public systems should be legible to the public.

What worries me is not only some cartoon version of Orwell. It is the boring version: safety dashboards, risk scores, fraud detection, productivity analytics, immigration enforcement, “trust and safety”, compliance automation, procurement contracts.

The boot does not always arrive as a boot. Sometimes it arrives as infrastructure.

And the hard question is not whether surveillance can create order. It obviously can. So can a prison.

The question is whether it creates accountable power afterwards.

A panopticon may produce “best behaviour”, but only by turning citizens into managed subjects. I have been trying to understand this fetish for controlling people through coercion that seems so prevalent in certain new modern business contexts, like amazon warehouse workers and delivery employees.

The only thing it creates is resentment. Is that how you want to build a company or society on. Resentment?

I’m working on something close to that. At the moment it’s just for ableton. The idea is to be able to sync a daw project, binaries will be saved on cloudflare and then use git for certain cases where it’s possible to merge. In case one person is working on a bass line and another is working on a guitar part. I’ve been using git for this workflow but the idea to have use interface that’s legible for non git users

I think the article make some great points, however this part is not even wrong:

"The obvious objection is that code produced at that speed becomes unmanageable, a liability in itself. That is a reasonable concern, but it largely applies when agents produce code that humans then maintain. Agentic platforms are being iterated upon quickly, and for established patterns and non-business-critical code, which is the majority of what most engineering organizations actually maintain, detailed human familiarity with the codebase matters less than it once did. A messy codebase is still cheaper to send ten agents through than to staff a team around. And even if the agents need ten days to reason through an unfamiliar system, that is still faster and cheaper than most development teams operating today. The liability argument holds in a human-to-human or agent-to-human world. In an agent-to-agent world, it largely dissolves."

LLMs are not conscious, that means left on their own devices they will drift. I think the single most important issue when working with LLMs is that they write text without a layer that are aware what's actually being written. That state can be present in humans as well, like for example in sleepwalking.

Everyone who's tried to to complete vibe coding a somewhat larger project knows that you only get to a certain level of complexity until the model stops being able to reason about the code effectively. It starts to guess why something is not working and cannot get out of that state until guided by a human.

That is not new state in the field, I believe all programmers has at points in their career come across code that's been written with developers needing to get over a hard deadline with the result of a codebase that cannot effectively be modified.

I think for a certain subsets of programming projects some projects could possibly be vibe coded as in that code can be merged without human understanding. But it has to be very straightforward crud apps. In almost everything else you will get stopped by slop.

I suspect that the future of our profession will shift from writing code to reading code and to apply continuous judgement on architecture working together with LLMs. Its also worth keeping in mind that you cannot assign responsibility to an LLM and most human organization requires that to work.

I think some type of tickets can be done like this but your trusted user assumption does a lot of work here. Now I don't see this getting better than that with the current architecture of LLMs, you can do all sorts of feedback mechanisms which helps but since LLMs are not conscious drift is unavoidable unless there is a human in the loop that understands and steers what's going on.

But I do think even now with certain types of crud apps, things can be largely automated. And that's a fairly large part of our profession.

Possibly, but probably not in less time and the point was partly learn to use agentic coding and also having it do exactly what I wanted.

I’ve done a event ticket system that’s in production. Stripe integration, resend for mailing and a scan app to scan tickets. It’s for my own club but it’s been working quite well. Took about 80 hours from inception to live with a focus on testing.

I’ve done some experiments with reading gedcom files, and I think I’m quite close to a demoable version of a genealogy app.

Biggest thing is a tool for remotely working musicians. It’s about 10000 lines of well written rust, it is a demoable state and I wish I could work more on it but I just started a new job.

But yeah, this wouldn’t have been possible if I hadn’t been a very experienced dev who knows how to get things live. Also I’ve found a way to work with LLMs that works for me, I can quickly steer the process in the right way and I understand the code thats written, again it’s possible that a lot of real experience is needed for this.

I don’t really find “can the model produce good code?” that interesting anymore. In the right workflow, it plainly can. I’ve gotten code out of LLMs that is not just faster than I’d write by hand, but often better in the ways that matter: tests actually get written, invariants get named, idempotency is considered, error conditions don’t get silently handwaved away because I’m tired or trying to get somewhere quickly.

When I code by hand under time pressure, I’m actually more likely to dig a hole. Not because I can’t write code, but because humans get impatient, bored, optimistic and sloppy in predictable ways. The machine doesn’t mind doing the boring glue work properly.

But that is not the real problem.

The real problem is what happens when an organisation starts shipping code it does not understand. That problem predates LLMs and it will outlive them. We already live in a world full of organisations that ship bad systems nobody fully understands, and the result is the usual quagmire: haunted codebases, slow change, fear-driven development, accidental complexity, and no one knowing where the actual load-bearing assumptions are.

LLMs can absolutely make that worse, because they increase the throughput of plausible code. If your bottleneck used to be code production, and now it’s understanding, then an organisation that fails to adapt will just arrive at the same swamp faster.

So to me the important distinction is not “spec vs code”. It’s more like:

• good local code is not the same thing as system understanding

• passing tests are not the same thing as meaningful verification

• shipping faster is not the same thing as preserving legibility

The actual job of a programmer was never just to turn intent into syntax anyway. Every few decades the field reinvents some story about how we no longer need programmers now: Flow-Matic, CASE tools, OO, RUP, low-code, whatever. It’s always the same category error. The hard part moves up a layer and people briefly mistake that for disappearance.

In practice, the job is much closer to iteratively solving a problem that is hard to articulate. You build something, reality pushes back, you discover the problem statement was incomplete, the constraints were wrong, the edge case was actually central, the abstraction leaks, the user meant something else, the environment has opinions, and now you are solving a different problem than the one you started with.

That is why I think the truly important question is not whether AI can write code.

It’s whether the organisation using it can preserve understanding while code generation stops being the bottleneck.

If not, you just get the same bad future as before, only faster, cleaner-looking, and with more false confidence.

This was my first literary experience, my mother read it to me when I was three years old. Seeing Janssons rendering of Smaug made me remember it was this version she read for me.