@doruktarhan6@_mayy00_@GergelyOrosz wdym here by a good state tracking system?
like performing something similar to a /compact or a summarize and then store it ?
@cfa_ind@thevarrun This is such a critical piece . every socioeconomic strata of india needs to be educated about this.
Atleast they would diversify their assets across banks as a defense.
And vote better as an attack
@Romy_Holland@valtism@Aella_Girl I assume they started sort of middle class and saved and worked their way to upper middle class.
But again the environment was conducive for this
I've plotted the most expensive McDonald's burger and the least expensive MacBook over time. This analysis projects that the most expensive burger will be more expensive than the cheapest laptop as soon as 2081
AGENTS dot md files don't scale beyond modest codebases.
Lots of discussions on this lately.
If you're building serious software with Claude Code or any agentic tool, a single AGENTS dot md will eventually fail you. This paper shows what comes next.
A 1,000-line prototype can be fully described in a single prompt. A 100,000-line system cannot. The AI must be told, repeatedly and reliably, how the project works, what patterns to follow, and what mistakes to avoid.
Single-file manifests hit a ceiling fast.
This new paper, Codified Context, documents a three-tier infrastructure built during real development of a 108,000-line C# distributed system across 283 sessions over 70 days.
The system uses a three-tier memory architecture: a hot-memory constitution (660 lines, always loaded), 19 specialized domain-expert agents (9,300 lines total) invoked per task, and a cold-memory knowledge base of 34 specification documents (~16,250 lines) queried on demand via an MCP retrieval server.
Across 283 sessions, this produced 2,801 human prompts, 1,197 agent invocations, and 16,522 autonomous agent turns, roughly 6 autonomous turns per human prompt, with a knowledge-to-code ratio of 24.2%.
Crucially, none of it was designed upfront: each new agent and specification emerged from a real failure, a recurring bug, an architectural mistake, a convention forgotten, and was codified so it could never require re-explanation again, turning documentation into load-bearing infrastructure that agents depend on as memory, not reference.
Paper: https://t.co/ZXBzhhkzsq
Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX
@Exec2Owner @TechLayoffLover After epstein files, I believe people will do anything to benefit thenselsvesand fulfill their absurd goals woth no thought about morality or what's fair
It's exactly 8 years since I published this on Nov 6, 2016. My first step down the rabbit hole that became Facebook/Cambridge Analytica. And if you still think that's a 'conspiracy', I have a social media platform to sell you.
2/
https://t.co/lxqNOUcopJ
@AirKills @OwenBenjamin @mehtaversed "Our money" yup thank you for transferring me my salary every fortnight from your checking account...
Nothing is unearned.
@TheStevenBraun @notPBD I seriously don't think cooks and truck drivers are coming in on h1b. Maybe a celebrity chef but even they have a diff visa category for that I would think