63 links · newest first
A GitHub repository by Andrej Karpathy for llm.c, a project focused on implementing and experimenting with large language models in C. The page serves as the repository landing page, with standard GitHub project metadata, code, and related documentation links.
Visit originalSam Witteveen reviews the newly released Qwen3.8-27B model, comparing its Hugging Face versions, fine-tunes, and quantizations, and testing different reasoning levels (finding medium reasoning offers the best balance while X-high reasoning can burn tens of thousands of tokens). Using an RTX Pro 600…
Visit originalThe article covers PrismML's Bonsai model, based on Alibaba's Qwen3.6-27B, which compresses a 27-billion-parameter model from 54GB at FP16 to under 4GB using ternary and 1-bit quantization. It explains memory-bandwidth-bound inference, ternary quantization math, metadata overhead, quantization-awar…
Visit originalThis Towards Data Science article describes a deterministic, dependency-safe prompt-pruning pipeline for long-running LLM conversations that avoids extra LLM calls or embeddings. It uses three passes—expired context elimination, duplicate context elimination, and dependency restoration—to remove re…
Visit originalThis MarkTechPost article covers Google Research's introduction of TabFM, a foundation model for tabular data that performs zero-shot classification and regression without dataset-specific training or feature engineering. The model treats an entire table as a single prompt, using in-context learnin…
Visit originalThis VentureBeat article covers DeepSeek's open-source release of DSpark, an MIT-licensed speculative decoding framework designed to make large language models generate tokens faster without changing outputs. It explains how DSpark combines semi-autoregressive drafting with confidence-scheduled ver…
Visit originalThis AIbase news article reports that MiniMax officially open-sourced its native multimodal flagship model, MiniMax M3, with 428B total parameters and 23B active parameters. The model reached the top of a global open-source intelligence index within two weeks and doubled its response speed, with st…
Visit originalThis VentureBeat article covers Google's release of Gemma 4 12B, an 11.95B-parameter open-weights model under Apache 2.0 license optimized to run locally on a typical 16GB enterprise laptop. It explains the model's encoder-free 'Unified' architecture for processing raw audio and video, its 256K tok…
Visit originalThis Substack article by Fei-Fei Li argues that spatial intelligence, not just language, is the next major frontier for AI, since current LLMs and multimodal models remain limited in understanding the physical world. It defines 'world models' as the key technical approach, covering generative, mult…
Visit originalThis VentureBeat article explains how DeepSeek's V4 Pro and V4 Flash models use cache compression and memory offloading to sharply cut token and infrastructure costs compared to Western frontier models. It cites benchmark and pricing data showing enterprise adoption shifting away from closed labs l…
Visit originalThis InfoWorld article explains how small language models (SLMs) differ from large language models through techniques like knowledge distillation, pruning, quantization, and LoRA fine-tuning. It outlines SLM benefits such as lower compute costs, faster inference, stronger privacy, and better fit fo…
Visit originalThis MarkTechPost article covers OpenMythos, an open-source PyTorch project attempting a first-principles reconstruction of Anthropic's unreleased "Claude Mythos" architecture, theorized to be a Recurrent-Depth Transformer. It details supporting techniques including Mixture-of-Experts layers, Multi…
Visit originalVentureBeat covers the release of Mamba-3, an open-source language model built on State Space Models designed to improve inference efficiency compared to Transformers. It matches Mamba-2's perplexity while using half the state size, using complex-valued states and a generalized discretization metho…
Visit originalMarkTechPost reports that Alibaba's Qwen team released Qwen3.5, led by a 397B-parameter sparse Mixture-of-Experts model with 17B active parameters per forward pass, a 60-layer hybrid architecture, and support for 201 languages. It highlights native vision-language training, Model Context Protocol s…
Visit originalThis Lex Fridman Podcast episode features Nathan Lambert and Sebastian Raschka discussing the state of AI in 2026, focusing on LLMs, scaling laws, and pre-training, mid-training, and post-training. The conversation covers AI coding, open source versus closed source models, long context, tool use, c…
Visit originalThis is the YouTube video of Lex Fridman Podcast #490, featuring Nathan Lambert and Sebastian Raschka discussing the state of AI heading into 2026, including US-China competition and open versus closed-weight models. They explain transformer architecture, pre/mid/post-training, scaling laws, RLHF, …
Visit originalThis LinkedIn post by Sivasankar Natarajan explains what happens inside an LLM workflow when a prompt is sent, dividing the process into input processing, transformer block computation, and prediction/generation phases. It describes token embeddings, positional embeddings, multi-head self-attention…
Visit originalMIT CSAIL researchers introduced recursive language models (RLMs), an inference framework that treats long prompts as an external environment so LLMs can inspect, decompose, and recursively process snippets with code rather than fitting everything into the context window. A root model orchestrates …
Visit originalThis article argues the 'bigger is better' approach to language models is ending as Small Language Models (SLMs) increasingly outperform or replace larger LLMs in enterprise settings. It cites Gartner's prediction that organizations will use SLMs three times more than general-purpose LLMs by 2027, …
Visit originalThis technical article covers Google Research's TITANS architecture, which applies cognitive-science-inspired ideas to AI memory, including multiple memory systems operating at different timescales, a surprise mechanism for encoding, and adaptive forgetting. It reports that models with 170M to 760M…
Visit original