AI Research & Science
Research
Cursor’s Composer 2.5 matches Opus 4.7 and GPT-5.5 benchmarks at a fraction of the cost
Source Read original →
AI Guides & Tutorials
GuideGuide
Take your local GitHub sessions anywhere
The best GitHub Copilot workflows don’t happen one–thing–at–a time. You might have an agent refactoring a module in…
AI Research & Science
Research
Benchmarked Kokoro 82M vs Supertonic 3 TTS on CPU
Wanted a real head to head on the two TTS models that actually run well on CPU. Couldn’t…
AI Research & Science
Research
The Open Agent Leaderboard
The Open Agent Leaderboard How good are general purpose AI agents? We built an open evaluation framework to…
AI Research & Science
Research
Podcast: The Physical Politics of the Internet with Britt Paris
As you scroll around the web, how often to you think about the physical infrastructure—the miles of cables,…
AI Research & Science
Research
Quantizing MTP KV Cache = free lunch?
With the MTP llama.cpp implementation in the Qwen3.6/3.5 models more VRAM is required for the MTP layer. However,…
AI Research & Science
Research
Qwen 3.6 27B on 24GB VRAM setup: backend comparisons, quant choice and settings (llama.cpp, ik_llama.cpp, BeeLlama, vllm)
TL;DR best setup I tested on a RTX 3090 24 GB: ik_llama.cpp + Qwen3.6-27B-MTP-IQ4_KS.gguf 156k context, q8_0/q8_0 KV,…
AI Guides & Tutorials
GuideGuide
model-agnostic sensitivity approximator [P]
(to preface, i’m 16 and this is the first package i’ve ever built. any feedback would be appreciated!)…
AI Research & Science
Research
Big new memory tool with local benchmarks
NOT MINE: https://github.com/rtk-ai/icm Knowledge retention: Agent recalls specific facts from a dense technical document across sessions. Session 1…
AI Research & Science
Research
I built a coding agent that gets 87% on benchmarks with a 4B parameter model, here’s how
I was frustrated that every coding agent (OpenCode, Cursor, Claude Code) assumes you’re running GPT-5.4 or Claude Opus.…