Viewing profile — beshrkayali

This is hilariously true > AI risk is string theory for computer programmers. It's fun to think about, interesting, and completely inaccessible to experiment given our current tech…

Should’ve probably said “attempted at defining” instead of “defined”.

It can’t, unless you descend into sophistry. We came up with and defined the word “consciousness” specifically to fit our own understanding of the collection of behaviors we do tha…

In the case of Claude or others, it is not just an advertisement, it's the weird shape the industry is spinning LLM-assisted-coding as a "co-author" relationship where it should be…

> But they’re hamstrung by the terminal itself, which is almost always monospaced and thus fatiguing to read. Not related to the main point of the article, but I find reading long …

Everyone is trying to figure out how and what are the optimal use cases. It could be like you said but it doesn’t have to be. There’s a lot of incentive for it not to end up like t…

For now it’s the exact same reason why you’d use Python when you’re writing by hand: so the code is more easily readable/editable by humans who are more likely to know Python than …

Humble mention, I’ve been thinking the same thing with Ossature for the last couple of months since I started working on it: https://ossature.dev The models are already good enough…

[dead]

[dead]

I wrote something similar recently about how agent-generated code lacks the institutional memory that human-written code has. There's nobody to ask why a decision was made (1). “Sp…

The title of the article is more on the sensationalist side unfortunately, the actual paper gives a different view [1]. There are two parts worth quoting: > Although cortical reduc…

Exactly, and it is a DAG (specs and tasks in the toml plan). Check the QOIzig example and its task graph if you’re curious!

Exactly this. The audit pass in Ossature is specifically for that "unclear spec" case, you resolve ambiguities in the spec before generation starts rather than discovering them mid…

Allium looks interesting, making behavioral intent explicit in a structured format rather than prose is very close to what I'm trying to do with Ossature actually. Ossature uses tw…

All three of these are real. The audit pass in Ossature is meant to catch the first two before generation starts, it reads across all specs and flags underspecified behavior, missi…

Very much the same thinking. Ossature already structures work that way at the plan level during audit, so curious to see where you take it. Happy to share more about the TOML appro…

The hierarchy you describe (intent -> plan -> code -> tests) maps well to how Ossature works. The difference is that your approach builds scaffolding around Claude Code to recover …