Viewing profile — amangsingh

FaultWall sounds like we're absolutely on the same paranoid wavelength. Treating the LLM as a hostile/untrusted actor at the data plane is the only way this scales to enterprise. T…

Spot on regarding the automod. Unfortunately, the way I naturally structure my writing almost always triggers a 50/50 flag on AI content detectors. It is the absolute bane of my ex…

I looked into lat.md. They are definitely thinking in the same direction by using a CLI layer to govern the agent. The key difference is the state mechanism. They use markdown; I u…

To clarify the architecture: The LLM doesn't have access to the ledger. That’s the entire point of Castra. The LLM only has access to the CLI binary. The SQLite database is AES-256…

[dead]

Thanks! This took a while (approximately 30 days) to get to this point. The market basically relies on two main alternative approaches right now, both of which have their merits: 1…

[dead]

Good question. I did think about behaviour trees early on, but I realized they optimize for the wrong thing in this specific domain. Behaviour trees are fantastic for agent autonom…

[dead]

Just dropped the Show HN here: https://news.ycombinator.com/item?id=47601608 . Would love to hear your thoughts on the architecture!

Just posted it here: https://news.ycombinator.com/item?id=47601608 Thank you so much for the coffee offer, that genuinely made my day! I don't have a sponsor link set up. Honestly,…

I got tired of AI agents forgetting what they were doing the moment their context window filled. The current industry solution is to write massively bloated agent harnesses full of…

Bingo. And them 'being careful' is exactly what bloats it to 500k lines. It's a ton of on-the-fly prompt engineering, context sanitizers, and probabilistic guardrails just to keep …

Claude code is a massively successful generator, I use it all the time, but it's not a governance layer. The fact that the industry is copying a 500k-line harness is the problem. W…

Why not both? AI writes bloated spaghetti by default. The control plane needs to be human-written and rigid -> at least until the state machine is solid enough to dogfood itself. T…

Herding cats is treating the LLM's context window as your state machine. You're constantly prompt-engineering it to remember the rules, hoping it doesn't hallucinate or silently dr…

If writing concise architectural analysis without the fluff makes me an AI, I'll take the complement. But no - just a tired Architect who has spent way too many hours staring at br…

A 500k line codebase for an agent CLI proves one thing: making a probabilistic LLM behave deterministically is a massive state-management nightmare. Right now, they're great for pr…