📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Updated 2026-06-06 00:08:19 +02:00
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Updated 2026-06-05 11:00:02 +02:00
Hypernetworks that update LLMs to remember factual information
Updated 2026-05-25 09:12:27 +02:00
Self-bootstrapping recipes for open base LLMs — 14B reaches 80% on HumanEval with no human-written training data. Code, mined pairs, and reproduction guide for the paper.
Updated 2026-05-13 18:09:54 +02:00
Flakestorm — Automated Robustness Testing for AI Agents. Stop guessing if your agent really works. FlakeStorm generates adversarial mutations and exposes failures your manual tests and evals miss.
Updated 2026-04-16 03:21:38 +02:00
asynchronous semantic prompt/response cache for llm apis
Updated 2026-04-01 12:25:48 +02:00
I replicated Ng's RYS method and found that duplicating 3 specific layers in Qwen2.5-32B boosts reasoning by 17% and duplicating layers 12-14 in Devstral-24B improves logical deduction from 0.22→0.76 on BBH — no training, no weight changes, just routing hidden states through the same circuit twice. Tools included. Two AMD GPUs, one evening.
Updated 2026-03-20 02:51:23 +01:00
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Updated 2026-01-21 11:12:32 +01:00