stantonius

adding friction back into development

I'm really trying to do this too. The problem is it's *so easy* to let your standards slip, even for just a moment, and that piece of code suddenly becomes foreign.

I find more mental energy is spent on restraint than execution these days.

Yeah I can understand that, and sure this is part of it, just not all of it. There is also broader societal issues (ie. inequality), personal questions around meaning and purpose, and a sprinkling of existential (but not much). I suspect anyone surveyed would have a different formula for what causes this unease - I struggle to define it (yet think about it constantly), hence my comment above.

Ultimately when I think deeper, none of this would worry me if these changes occurred over 20 years - societies and cultures change and are constantly in flux, and that includes jobs and what people value. It's the rate of change and inability to adapt quick enough which overwhelms me.

I feel this way too. Wish I could fully understand the 'why'. I know all of the usual arguments, but nothing seems to fully capture it for me - maybe it' all of them, maybe it's simply the pace of change and having to adapt quicker than we're comfortable with. Anyway best of luck from someone who understands this sentiment.

You know, there aren’t many people whose communication style, approach, and contribution history earn my confidence so completely. I can probably count on two hands the people I hold in that regard in this industry. Mario and Armin are two of them. It’s incredibly hard to build trust online these days, but there’s something about this Viennese crew that I like.

This was a solid letter to the fans. I get why it’s disappointing to some, but it sounds like it was the right move for them personally. For people who’ve earned that kind of credibility, I say congrats on the move.

Wrt simonw, I think that is unfair. I get the hype is frustrating, and this project made everything worse (I also feel it and it drives me nuts too), but Simon seemed to choose the words quite carefully. Over the weekend, his posts suggested (paraphrasing) it was interesting, funny, and a security nightmare. To me, this was true. And there was a new post today about how it was mostly slop. Also true.

Btw I'm sure Simon doesn't need defending, but I have seen a lot of people dump on everything he posts about LLMs recently so I am choosing this moment to defend him. I find Simon quite level headed in a sea of noise, personally.

There's something eerily recursive about Opus 4.5’s sensible take calming the anxiety about Opus 4.5’s capabilities and impact. It's probably the right take, but I feel weird the most pragmatic response to this article is from said model.

This is so relatable it's painful: many many hours of work, overly ambitious project, now feeling discouraged (but hopefully not willing to give up). It's some small consolation to me to know others have found themselves in this boat.

Maybe we were just 6 months too early to start?

Best of luck finishing it up. You can do it.

This happened to me too in an experimental project where I was testing how far the model could go on its own. Despite making progress, I can't bare to look at the thing now. I don't even know what questions to ask the AI to get back into it, I'm so disconnected from it. Its exhausting to think about getting back into it; id rather just start from scratch.

The fascinating thing was how easy it was to lose control. I would set up the project with strict rules, md files and tell myself to stay fully engaged, but out of nowhere I slid into compulsive accept mode, or worse told the model to blatantly ignore my own rules I set out. I knew better, but yet it happened over and over. Ironically, it was as if my context window was so full of "successes" I forgot my own rules; I reward-hacked myself.

Maybe it just takes practice and better tooling and guardrails. And maybe this is the growing pains of a new programmers mindset. But left me a little shy to try full delegation any time soon, certainly not without a complete reset on how to approach it.

I've always conducted my thoughts in an "uncompressed format" and then eternally struggled to confine it all into words. Only then for people to misinterpret and question it.

This resonates so much with me. To a point where I don't write/contribute in public forums out of fear for this misinterpretation.

Strangely, your post has made me push through that exact fear to write this, so any perceived misinterpretation has positively impacted at least one stranger. This is a good reminder for me that focusing only on negative consequences misses the unintended positive ones of still putting something out there, even if its not a perfect representation of the "uncompressed format".

Thank you for sharing, and I wish you a speedy recovery.

I only read the headline and got enough from it. It was a good reminder that romanticising entrepreneurship is exciting and fun but the reality is much different, and to appreciate your current circumstance more (the grass is always greener, etc etc)

I increasingly find that I need these quick hits to refocus and prioritise...

I have found working with DSPy to be a nice middle ground. The python script contains functions that call different DSPy optimizers (the optimized prompt packaged as a function; tested and iterated individually in a Jupyter notebook). Using DSPy `TypedPredictors` returns structured output that I then parse (ie. with conditions/loops) within the larger python script.

Can't say for sure yet if the project will work, but this workflow seems OK because DSPy abstracts away the CoT optimization with still giving me full control of the inputs/outputs in a python multi-agent script