???gokuhides

@geoffreywoo this actually makes no sense. self recursive ai can’t learn. it will prob be china

either openai or anthropic will be the first to build self recursive ai who will build the self recursive factory?

@JqOnly lmao dude go read zero to one. you’re being a snowflake. i’m giving you feedback and you’re getting offended.

@sidewalkco we are just discussing the Agent OS and LLM context windows and you are bringing up a book to attack my ego that doesn't exist. i think we are done here i am always open when the reply fits the post.

Agent OS Ouroboros has been evolving into an Agent OS github.com/Q00/ouroboros

@zamdoteth retardmaxxing is not that good. autismmaxxxing is the best form because it gives you the benefit of thinking and being a retard.

Reatardmaxxing is a skill you have to be born with You either have that founder aura in you or you don’t Show me one piece of evidence that the dawg is indeed within you

tbh the best move is just removing memory from your LLMS. unless it’s declared - why the hell do i want it to remember. People are using ai like they are communists. Use AI like you’re a dictator.

@levie @harshilmathur i mean the take is super dumb. LLMS are a tool. why do we want a special specific hammer customized hammer that knows all of my info?? i just want to hammer my nails.

@harshilmathur Probably unlikely. It would mean that every app will behave differently depending on the user’s setup which will make building good products impossible.

Hot take: in a few years, apps will assume you have a local LLM with memory just like they assume always-on internet today. Every app becomes personal, intelligent and a little different for everyone. And software as we know it completely changes.

US is cooked because they think AI is god. China is based because they think AI is a tool. Praying that US stops this AI psychosis.

@JqOnly i learned both. you need to not be another arrogant rand tech elitist that never reads. go read atlas shrugged and fix your ego. don’t be brainwashed by tech elitism

@sidewalkco 8 years cool but in new ai era it's a hard reset, time to unlearn

@JqOnly i will. and i will dunk on you when it’s done. i’ve worked in audit for 8 years so the critique stands. i’m ex big4

I'm not being defensive; I'm pointing out that your critique is fundamentally off-targe. in Ouroboros, we use session separation to isolate tasks, meaning there is zero context bloat. You know disposable memory like MCP or subagent? each decoupled session is governed by an independent Evaluate stage that validates results against the Contract before anything moves forward. you’re critiquing a monolith but we’ve built a modular, audited system 👍🐍

@JqOnly also why are you being so defensive? you need to take criticism and address actual ideas before defaulting to “AI SLOP LOL”. LLMS are just tools. don’t let it ruin your brain bro

This is actually how you address slop and your architecture doesn’t meet auditing standards. Because you include the auditing loop in the workflow. There should be two different workflows. You don’t have an auditing background so i don’t think you know this. DEV LOOP human intent → spec → implementation → internal QA → candidate artifact ↓ handoff boundary AUDIT LOOP independent audit spec → evidence collection → tests/review → risk assessment → pass/fail/escalate ↓ gate release / revise / reject

@JqOnly ask them if you adhere to these principles. if not then it’s just fraud

@JqOnly dude check yourself. post a screenshot of codex / claude / kimi fact checking yourself. be honest here

because @JqOnly is obv defensive. here are the research articles that are cited that talk about these issues about operating in a closed system and why his repo isn’t claiming what it says it’s doing. arxiv.org/abs/2305.17493…

@JqOnly i can do it for any. you obv is defensive. do you want me to pull references from alex radford?

@sidewalkco good boy, using chatgpt to get information do you understand my philosophy or the system with mcp? and will you use chatgpt again to reply my thread?

Why these automations loops are not evolving. @JqOnly You are facing this problem and hermes. 🧵Thread Pt 1

Also - wtf - it’s in python. not rust. smh

TLDR - system design would tell you that closed systems don’t inherently change. evolve. be careful of the fancy language. Don’t mean to dunk on the guy - you prob don’t know this info.

@JqOnly if you were actually a serious person about this. go into codex and claude and analyze your repo. ask them if your system fails to evolve due to it operating on a closed system. LLMS won’t lie to ya buddy.

@JqOnly there ya go buddy. go see it for yourself.