Subscribe
Archive / page 94 of 123

Latest articles, page 94

  1. Linear Attention and Retentive Networks: How Recurrent Duals and Chunkwise Tiling Eliminate the Quadratic Bottleneck

    Linear Attention and Retentive Networks: How Recurrent Duals and Chunkwise Tiling Eliminate the Quadratic Bottleneck Autoregressive large language models built on standard multi-head self-attention face two fundamental scaling ceilings: quadratic compute and memory complexity during pre-training, and linearly expanding key-value (KV) cache memory footprints during autoregressive generation. While optimizations such as FlashAttention reduce memory access overheads and Grouped-Query Attention (GQ

    Architecture
    8 min read

  2. Tool Retrieval and Dynamic Function Selection in Production AI Agents: Architecture, Semantic Indexing, and Serving Trade-Offs

    Tool Retrieval and Dynamic Function Selection in Production AI Agents: Architecture, Semantic Indexing, and Serving Trade-Offs The default approach to LLM tool calling—stuffing every function schema into the prompt—works for demos with a dozen tools. It fails in production where agents face hundreds or thousands of available functions. Context windows saturate, selection accuracy degrades, and latency grows linearly with registry size. This post surveys the architectural progression from stati

    AI
    6 min read

  3. Relativity Networks Raises $22M and Lands $40M Hyperscaler Deal for Hollow-Core AI Data Center Fiber

    Optical fiber startup Relativity Networks has secured $22 million in SAFE note funding and booked a $40 million follow-on order from an unnamed hyperscaler to deploy hollow-core fiber across distributed AI data center facilities. The funding round included participation from Rhapsody Venture Partners, Bell Ventures Inc., and Faster Than Glass LLC. The capital will support scaling production and deployment of hollow-core fiber cables engineered specifically for low-latency interconnects between

    AI
    2 min read

  4. Knowledge Editing in Large Language Models: How Causal Tracing, ROME, and MEMIT Modify Factual Storage in MLP Weights

    Updating factual information in pre-trained large language models has traditionally required two imperfect extremes: computationally expensive continual pre-training, or external prompt-stuffing through Retrieval-Augmented Generation (RAG). Standard gradient descent fine-tuning on isolated facts leads to catastrophic forgetting, parameter drift, and degraded general reasoning. To solve this, mechanistic interpretability researchers introduced direct model editing: a paradigm that treats transfo

    AI
    6 min read

  5. MIT, Stanford, and 12 Academic Labs Launch Public AI Observatory to Track Real-World LLM Usage

    A consortium of researchers from MIT, Stanford University, and 12 other academic institutions has launched the Public AI Observatory (ai-observatory.org), an independent, auditable data repository designed to measure how individuals interact with artificial intelligence assistants in real-world settings. The initiative aims to address the empirical opacity surrounding commercial LLM deployment. While frontier AI developers such as OpenAI and Anthropic periodically release aggregated user metric

    research
    1 min read

  6. DDR5 Memory Prices Climb 500% in 12 Months as AI Hyperscalers Corner Global DRAM Capacity

    Spot and contract prices for standard DDR5 dynamic random-access memory (DRAM) have climbed by up to 500 percent over the past 12 months, driven by hyper-scaler procurement teams reserving global semiconductor fabrication lines for enterprise AI accelerator memory. Historical retail and channel tracking data compiled by PCPartPicker and reported by Tom's Hardware highlights severe price spikes across high-density modules. A 128GB DDR5-6400 kit that carried an all-time low of $329 now retails fo

    Hardware
    2 min read

  7. Vision-Language Model Architectures: How Vision Encoders, Token Projectors, and Dynamic Resolution Bridge Modalities

    Modern large language models operate exclusively on discrete sequences of token embeddings. Integrating visual perception into these systems requires converting continuous, two-dimensional spatial arrays into linear sequences of embedding vectors that match the dimensionality and distribution of the language model's hidden states. Vision-language models (VLMs) like LLaVA, Flamingo, Qwen2-VL, and InternVL accomplish this conversion through a three-stage pipeline: a vision encoder, a cross-modal

    AI
    7 min read

  8. GUI Agent Architectures in Production: Visual Grounding, DOM vs. Pixel Parsing, and Action Spaces

    Graphical user interface (GUI) automation has undergone a structural transition from programmatic DOM manipulation to vision-based foundation agents. Where earlier browser automation relied on CSS selectors, XPath expressions, and accessibility trees, modern desktop and cross-platform agents interact with operating systems through raw pixel observations and virtual input devices. Deploying GUI agents in production environments introduces distinct engineering constraints. Visual grounding precis

    AI
    6 min read

  9. Pathway Secures $30M Seed at $500M Valuation to Scale BDH Post-Transformer Architecture

    AI research company Pathway has secured additional capital at a $500 million valuation, bringing its total seed funding to $30 million. The company is developing a post-Transformer architecture dubbed Baby Dragon Hatchling (BDH) designed to combine continuous in-weights adaptation, long-horizon reasoning, and memory within neural representations without relying on expanding KV caches or external retrieval pipelines. The BDH Post-Transformer Architecture Standard Transformer architectures suff

    AI
    2 min read

  10. Temporal in Talks to Raise $500M at $12B+ Valuation as Agent Orchestration Surges

    Developer infrastructure platform Temporal Technologies is in discussions to raise approximately $500 million in a new funding round that would value the company at over $12 billion pre-money, according to reports from Bloomberg. The financing represents a rapid increase in valuation from its $5 billion Series D round earlier this year, driven by accelerating adoption of durable execution runtimes for multi-step AI agents. The Shift Toward Durable Execution Runtimes While foundational model d

    AI
    2 min read