any · textlog

wrote:

ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so i’m happy to settle into predictable models for a while.

replied to:

I’ve found the same, albeit with Opus — it’s hard to find uses for Fable. I don’t need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.

replied to:

I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows. I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.

…

replied to:

same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so. also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.

replied to:

Coding probably yeah, but still they are bad at generating novel information, new ideas and such. They’re also not very good at seeing the bigger picture, they will narrowly perform the task but they’re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.

wrote:

Mind's empty. Heart's full. Desires? Average.

wrote:

Theory reuse > code reuse almost every time.

wrote:

'wade in the water.' isn't this the challenge of being 'ahead'? so many of us are waist deep in the same sea, it's hard to see what's in front of us vs. what's behind us. then we see the yacht boys sail by with their new masters, splashing us in their wake. then we grumble amongs

continued:

then we grumble amongst ourselves about 'that was my idea,' then carry on.

wrote:

I Built a Free Open Data Site for My Town

wrote:

I'm in bed and cannot sleep

What is a Textlog?

One of my favourite styles of Brazilian music is "Chorinho", and Luca Frazão is this new kid on the block who's just absolutely amazing:

wrote:

Good Morning from Flagstaff AZ!

wrote:

Happiness is having just enough hot water in my espresso to extend the experience without diluting it overmuch.

replied to:

Heaven is being able to experience it forever with each sip being as good as the last

wrote:

I’m an insane person who built their own coding harness, in Rust. I’ve called it Rho. Please forgive this landing page: https://rho-code.dev I just wanted an easy central spot.

replied to:

Not insane at all. People should build their own instead of using other people's agents. It's easy to do and the results can be great for you. I've built several; one that is effectively "stuck" in Kakoune:

replied to:

I wrote my own too. I feel like that's the best way.

…

replied to:

im decently happy with opencode. anything im missing out on?

replied to:

Yeah. It's a very large project with lots of dependencies. <The system prompt is long and wastes tokens. If you have ideas for tools (or automations like the agents.sh "loop" I wrote) it's easier if you understand the harness.

wrote:

Vagyis attól még, hogy trehány vagyok, még működhetne jobban is az anyagmegmaradás törvénye, mint éppen errefelé, vagyis errefelé pláne működnie kellene, mégsem ezt teszi.

So even though I'm clumsy, the law of conservation of matter could still work better than it does here, or rather, it shouldn't work here, but it doesn't.

wrote:

Anybody here actively working in or has contributed to (in any capacity) conservation (be it flora or fauna)?

…

replied to:

You know, as interesting as that sounds, I wouldn't at all know where to begin with something like that. Do you have a suggestion?

replied to:

I suggest looking around your area first, perhaps there are conservation groups already. Then, select among them which one focuses on native species that are most impactful to your place. 😁

wrote:

been building a voice first os using jev and some small voice models. I'm surprised how well it's working and I'm very close to the point where I can go into a feedback mode and tell it what behavior I want changed, it will spin up Claude or codex inside itself and setup the build to restart itself and continue with new code. tempted to let it build itself completely

replied to:

It sounds amazing! A voice first OS was also in my mind. Curious to hear more!

wrote:

Spent months pair-building a full telecom BSS with an AI. The surprise wasn't the code — it was that the real job became verification. The AI read 450 tokens for every 1 it wrote. Turns out building honestly is mostly re-reading.