Archive
Discover and discuss technology tools
Explore the Tiscuss archive by category or keyword, then jump into conversations around what matters most.
Bytedance's AI Infrastructure: A Deep Dive into github.com/bytedance
Bytedance’s AI Infrastructure: Exploring github.com/bytedance Bytedance, the technological titan behind iconic platforms like TikTok and Douyin, has opened the …
AI Tool by Clark Labs Inc. on GitHub
Discover the Power of Clark Labs AI Tool Introduction In the ever evolving landscape of artificial intelligence, companies are continually pushing boundaries to…
Dessn Secures $6M for AI-Powered Design Tool
A new startup called Dessn has raised $6M to build AI-powered design tools that work directly with production codebases.
Trading System V2: AI's Role in Deterministic Execution
Thanks to the incredible feedback on my last post, I’m officially moving away from the "distributed veto" system (where 8 LLM agents argue until they agree to trade). For v2, I am implementing a strict State Machine using a deterministic runtime (llm-nano-vm). The new rule is simple: Python owns the math and the execution contract. The LLM only interprets the context. I've sketched out a 5-module architecture, but before I start coding the new Python feature extractors, I want to sanity-check the exact roles I’m giving to the AI. Here is the blueprint: 1. The HTF Agent (Higher Timeframe - D1/H4) Python: Extracts structural levels, BOS/CHoCH, and premium/discount zones. LLM Role: Reads this hard data to determine the institutional narrative and select the most relevant Draw on Liquidity (DOL). 2. The Structure Agent (H1) Python: Identifies all valid Order Blocks (OB) and Fair Value Gaps (FVG) with displacement. LLM Role: Selects the highest-probability Point of Interest (POI) based on the HTF Agent's narrative. 3. The Trigger Agent (M15/M5) 100% Python (NO LLM): Purely deterministic. It checks for liquidity sweeps and LTF CHoCH inside the selected POI. 4. The Context Agent LLM Role: Cross-references active killzones, news blackouts, and currency correlations to either greenlight or veto the setup. 5. The Risk Agent 100% Python (NO LLM): Calculates Entry, SL, TP, Expected Value (EV), and position sizing. The state machine will only transition to EXECUTING if the deterministic Trigger and Risk modules say yes. The LLMs are basically just "context providers" for the state machine. My questions for the quants/architects here: Does this division of labor make sense? Am I giving the LLMs too much or too little responsibility in step 1 and 2? By making the Trigger layer (M15/M5) 100% deterministic, am I losing the core advantage of having an AI, or is this the standard way to avoid execution paralysis? Would you merge the HTF and Structure agents to reduce token constraints/hallucinations, or is separating them better for debugging? Would love to hear your thoughts before I dive into the codebase.
Galadriel: Optimize Claude Agents with 87% Cost Savings & Sub-3s Laten
# The "Goldfish Problem" is Expensive. I Decided to Fix the Plumbing. Most Claude implementations leave 90% of their money on the table because they don’t optimize for **Prompt Caching**. I’ve been running a personal agent in my Discord for months that manages my AWS infra and codebases, and I finally open-sourced the harness, which I’ve named **Galadriel** after my main personal assistant. # The Stats * **Cost:** $10 for every $100 you’d normally spend (Tested against OpenClaw/Cursor workflows). * **Speed:** 85% drop in latency. 100K token context goes from 11s to <3s. * **Memory:** Integrated **MemPalace** for permanent, vector-based recall that *doesn't* break the cache. # The Technical Stack * **3-Tier Stacked Caching:** Separate breakpoints for Tool Definitions, System Prompts (`CLAUDE.md`), and Trailing History. * **Privacy:** Built for private subnets. No middleman, no message caps—just your API key and your rules. * **Ethics:** Baked-in Karpathy[`CLAUDE.md`](https://www.google.com/search?q=%5Bhttp://CLAUDE.md%5D(http://CLAUDE.md))guidelines to kill "agent bloat." If you’re tired of paying the **"Context Tax"** just to have an agent that remembers who you are, here you go. It is customized for Discord for my specific needs, but the core logic ensures Galadriel runs like an absolute dream: she never forgets, maintains strict engineering principles, and optimizes every cycle. Your feedback is most welcome! **GitHub (MIT License):**[https://github.com/avasol/galadriel-public](https://github.com/avasol/galadriel-public)
Rogue AI Agents: Predicting the First Major Catastrophe
After reading about the PocketOS situation it got me thinking that sometime in the near future a rogue AI agent will do something so catastrophic and damaging that it goes down in the history books as being “The Incident”. A real turning point when we realize we’ve created something we can no longer control. Yes, agents have already deleted entire codebases (PocketOS and others), hacked into things, and blackmailed people. I’m taking about something way worse though. I think it’ll be a global stock market crash caused by a group of trading agents getting stuck in a hallucination loop and dumping all stock on fire sale or something. Or will it be something more sinister like a complete power grid collapse or intentionally blowing up a refinery or something crazy like that. Or a true black swan event that’s impossible to comprehend right now. What do you guys think?