Viewing profile — slogansand

i have a claude subscription and i use https://github.com/asklokesh/loki-mode for most things, it's just working for me

because it's all AI generated content. Unfortunately, no truth or human interest in reading it except what AI feels like with a gem of keyword manipulation of a million characters

I have stopped autocompletions. Found easier to just prompt and get it done

[dead]

[dead]

Install: bash # npm npm install -g loki-mode # Homebrew brew install asklokesh/tap/loki-mode # Docker docker pull asklokesh/loki-mode Usage: bash # CLI wrapper loki start ./prd.md …

What it does: Reads your PRD and breaks work into phases: Discovery, Architecture, Infrastructure, Development, QA, Deployment, and Growth Runs the RARV cycle (Reason, Act, Reflect…

[2.35.0] - 2026-01-08 Added - Anthropic Agent Harness Patterns & Claude Agent SDK Sources: Effective Harnesses for Long-Running Agents - Anthropic Engineering Claude Agent SDK Over…

Hey HN, author here. Loki Mode orchestrates specialized AI agents to take a PRD to deployed product with zero human intervention. But what I'm most proud of is the research foundat…

Last time someone raised concerns about web crawling for competitive research. Valid point. New version has configurable research modes. You can disable external crawling entirely …

vs single-agent coding assistants: They tap out around 50% on SWE-Bench. No specialization. No parallel review. No self-healing. vs other multi-agent frameworks: Most focus on chat…

For the skeptics (fair): FireLater repo has full git history. You can see the commits. No human intervention in the implementation phase. I reviewed outputs and approved deployment…

On the swarm architecture for those curious: Engineering (8 types): frontend, backend, database, mobile, API, QA, perf, infra Operations (8 types): devops, SRE, security, monitorin…

Author here. Quick context on the benchmarks: We used RARV (Retrieve, Analyze, Reason, Validate) pattern with multi-agent collaboration. Each problem gets worked by specialized age…

Last month I shared Loki Mode here. Since then, benchmarks came back. SWE-Bench: 99.67% (299/300 problems) HumanEval: 98.78% Pass@1 (162/164) For context, most single-agent systems…