The details are interesting: https://en.wikipedia.org/wiki/Eskom#Corruption

How much faster/slower are you with that process compared to writing code yourself?

Developer of 20+ years here, can't give you an accurate multiplier but I am faster.

Because spotting holes in specs has never been one of my strengths. And working without technical colleagues much of the time, it's a boon to be able to "rubber-duck" my ideas with something that is at least more intelligent than plastic.

Grabbing multipliers from thin air, the coding bit may only be 2x faster with a poorer-quality outcome, but working out what's needed is a good 5x faster.

And yes, I'm using the same adversarial AI MO as @wood_spirit, combined with Matt Pocock's excellent /grill-me and /grill-with-docs skills [1] and Plannotator [2] to review the plans.

1. https://github.com/mattpocock/skills

2. https://github.com/backnotprop/plannotator

I actually use LLMs a lot to rubber duck my problems and help develop plans. Then I manually code, to ensure my skills don't deteriorate. I feel like I'm a lot faster, with few of the downsides. Do you have any thoughts on this process?

If you can type code fast and accurately, it sounds a great process to use. You're using LLMs for the bit where they bring great value, and yourself as a higher quality coding agent :)

That's my take as well, I find fixing poor/overengineered LLM code taxing.

Have you considered incorporating formal modelling?

Like:

[0] https://csci1710.github.io/2026/ and https://forge-fm.github.io/book/2026/

[1] https://elliotswart.github.io/pragmaticformalmodeling/

[2] https://quint.sh/

Only at the "hmm that seems an interesting idea" level.

Thanks for the links, going to have a read and see if I can apply any to my work.

Thanks for sharing those. They look interesting.

Can't speak for GP or OP, but I see about 10x the output and 2-4x the value of what I would be able to get by hand. Within the gap between 2-4x and the 10x is really a lot of design documents, user/dev documentation and testing that I might not have rolled to nearly the extent that I do/get when using AI.

I haven't been using multiple AIs adversarially as OP, but might consider giving it a try with Codex and Opus. That said, my AI workflow has been pretty similar... lots of iterations on just design, then iterations on documentation, testing, etc... then iterations on implementation, testing, validation and human review in the mix.

My analogy is that it's really close to working with a foreign dev team, but your turnaround is in minutes instead of days, where it's much more interactive.

I'm seeing the same, for gains being largely from documentation.

I feel strong making "dev" documentation though, since it seems a bit redundant/superfluous. I fully suspect nobody is going to read it at this point.

Fair... but the AI will/may as you use agents for dealing with issues/bugs, etc.

For me, sometimes faster/sometimes slower, but there are a lot of other benefits besides speed:

* I can work in code I'm not familiar with much easier

* LLMs often identify confusion or uncertainty upfront, so I can address it earlier.

* I'm much less mentally taxed so I can go for longer at my top end.

* Meetings, disruptions, end of day is WAY less critical since I can lean on the LLM to get back into things.

* I can do something else productive while the LLM is running. Bug fixes, documentation, PR reviews, etc.

Having tried something similar, the perceived speedup does not, in the steady state, last.

To get a quality, lasting, result you're ultimately having to carefully study everything otherwise you end up quickly accumulating cognitive debt and the speedup soon shrinks as you're constantly having to revisit the initial approaches.

I use the latest codex with gpt5.4 and Claude opus every day. they hallucinate every day. If you think they don't, you are probably being gaslighted by the models.

I was interested in the human results, so I had an llm build a visualization for them: https://codepen.io/lovasoaaa/pen/QwKWGBd

You can see that 17% of answers come from India alone and that software developers got below average results, for instance.

This is amazing thanks for sharing!

The author of this project is also the author of redis. He knows what he is doing.

Running inference for a model, even when you have all the weights, is not trivial.

I use linux at home (with a HiDPI screen) and MacOS for work. The screen works well with both computers. I mostly just use a text editor, a browser, and a terminal though.

Linux has bugs, bug MacOS does too. I feel like for a dev like me, the linux setup is more comfortable.

Same here. I stick to 100% scaling and side step the whole hi dpi issue. I even have a single USB type c cable that connects my laptop to the laptop stand and that laptop stand is what connects to the monitor, keyboard, and mouse.

I know people will say meh but coming from the world of hurt with drivers and windows based soft modems — I was on dial up even as late as 2005! — I think the idea that everything works plug and play is amazing.

Compare with my experience on Windows — maybe I did something wrong, I don't know but the external monitor didn't work over HDMI when I installed windows without s network connection and maybe it was a coincidence but it didn't work until I connected to the Internet.

How do you call the opposite of green washing? When you want to show that you are burning as much energy on training models as the others.

Because we can

I use a fork of sqlx in SQLPage [1]. I think my main complaint about it is runtime errors (or worse, values decoded as garbage) when decoding SQL values to the wrong rust type.

* [1] https://sql-page.com/

A consortium of investigative journalists investigated and attributed the attacks the Ukraine's secret service: https://en.wikipedia.org/wiki/Nord_Stream_pipelines_sabotage