karpathy/nanochat is Andrej Karpathy's minimal, hackable Python/PyTorch harness for training a ChatGPT-style model end-to-end on one GPU node. GPT-2-grade model for about $48; 60,705 stars as of 19 November 2026.
Read ArticleExplore our latest tutorials, tech updates, and career advice written by industry experts to help you level up your skills.
karpathy/nanochat is Andrej Karpathy's minimal, hackable Python/PyTorch harness for training a ChatGPT-style model end-to-end on one GPU node. GPT-2-grade model for about $48; 60,705 stars as of 19 November 2026.
Read ArticleFareedKhan-dev/kimi-k3-in-c is a from-scratch portable C99 inference engine (Apache 2.0) running Moonshot AI's Kimi K3 on a single CPU — no GPU, no BLAS, no ML framework. A teaching artifact, not a daily driver.
Read ArticleParGLU (arXiv:2611.20663) pairs SwiGLU with ReLU² branches in a partially gated FFN. The paper reports it beats SwiGLU at 75M and 152M, with mixed results at 30M.
Read ArticleAnthropic launched Claude Fable 5.2 and Claude Mythos 5.2 on 9 Nov 2026 — up to 30% faster output than Fable 5.1, a 20% price cut, 1M-token context and an optional fast mode up to 2.5x faster.
Read ArticleGemini 4 Carbon reached general availability on 10 November 2026. It costs $2 input / $10 output per million tokens until 30 November; from 1 December 2026 every rate doubles to $4 input / $20 output.
Read ArticleAnthropic priced its IPO at $83.00 per share on 18 November 2026, above the $70–$78 range, for 980 million Class A shares on the Nasdaq Global Select Market (ticker ANT). First trading day: 19 November.
Read ArticleTencent released Hy4 flash on 16 November 2026, following Hy4 (4 Nov). It has 224 billion total parameters with 12 billion active per token, a 1-million-token context, and costs $0.07 input / $0.281 output per million tokens.
Read ArticleGemini 4 Hydrogen reached general availability on 12 November 2026. Built for everyday coding and agentic workflows, adapted from Carbon, with a 1-million-token context and a March 2026 knowledge cutoff.
Read ArticleMeta released Muse Ember on 9 November 2026 — its smallest and most efficient model, aimed at routine agent work such as tool calls, coding subtasks, routing and extraction, at $0.10 input / $0.50 output per million tokens.
Read ArticleBaidu released ERNIE 5.5 Flash Base on 5 November 2026 — a sparse mixture-of-experts base model with 280 billion total parameters and 14 billion active per token, with weights downloadable from Hugging Face.
Read ArticleAsk about courses, website & more
Request human callback:
Please log in to download. You will stay on this page after logging in!
New here? Register now →