The Archive

ChatGPT search adopts site: operator; Promptwatch tracks generative engine optimization trends across LLM chat products.

Businesses are willing to flop back and forth as each lab releases new models, volatility that should give both companies' investors pause about how "sticky" enterprise AI spending really is.

Ever wanted someone else to do your texting for you? ChatGPT is being offered up as an automated text scribe via a new Apple Messages integration.

Google will soon allow you to customize your Discover feed by describing what you want to see. The new feature, rolling out to the Google app in the "coming days," will use AI to automatically tweak your feed and "remember" your preferences for future visits. You'll find the option within the three-dot menu on your Discover feed. As shown in a video shared by Google, tapping the feature will open a chatbot-style interface, where you'll be able to describe your preferences. The chatbot will confirm your choices and lay out the types of content it will prioritize, but you'll also have the optio...

Matt Pocock describes a /wayfinder skill for clarifying direction on greenfield projects with uncertain requirements.

Jason Kelce joked that people should cool data centers with their pee, rather than potable water -- his suggestion is not completely ludicrous.

Google is giving publishers a new button that lets readers make them a preferred source across Search, Discover, and Google News, potentially boosting their traffic as AI search sends fewer clicks to the web.

Runlayer and Rippling have dropped their lawsuits. No money was paid. Rippling celebrated by releasing a competing product.

Linkdaze's smart digital calendar stands out for not putting its features behind a paywall, including an AI meal planner tool.

Martingale-based analysis recovers classical concentration inequalities (Ville, PAC-Bayes, Azuma-Hoeffding) via exact variational identities.

ConceptGuard benchmark evaluates LLM unlearning at concept level, measuring harmful behavior removal while preserving benign knowledge.

G-CARL introduces Patient-oriented Medical Report Interpretation (PMRI) task requiring multimodal models to generate evidence-grounded, accessible explanations of medical images.

TCP_α method improves post-hoc confidence estimation for music information retrieval via margin-controlled training on frozen classifiers.

Controlled comparison of FMCW radar, IR-UWB, and Wi-Fi sensing for ceiling-mounted healthcare monitoring and sleep detection.

Three-agent workflow integrates conversational data collection, processing, and travel behavior prediction using image-augmented surveys and weather scenarios.

Method induces reusable symbolic task models from passively recorded computer-use traces (screenshots, mouse/keyboard actions) for agent learning and organizational audit.

AI4AI-Bench isolates LLM agent capability to design training algorithms for recursive self-improvement, beyond hyperparameter tuning or data collection.

Pandora's Box framework optimizes routing across heterogeneous AI systems, balancing cheap noisy value estimators against expensive accurate ones.

BERT-LER pretrained on 75M-patient EHR dataset uses discrete laboratory tokens with percentile binning and Integrated Gradients for interpretable clinical prediction.

MidTool: open pipeline synthesizing tool-use training data from APIs, web, and code to improve agentic LLM capabilities via mid-training.

Statistical inference method for dictionary learning under calibration uncertainty; niche signal-processing contribution.

Affected users told TechCrunch they were using Grok Lite, and noticed the issues as early as Wednesday morning.

Study identifies seven measurement artifacts in LLM self-improvement claims; Qwen3-8B LoRA self-training masks false gains without proper null controls.

Causal graph learning from sleep apnea test data reveals population-stratified breathing dynamics; medical domain application.

ChatGPT and other AI models are now authoring and editing much of the new web.

IAR: three-stage post-training framework (inject, align, recover) for internalizing bounded document corpora into LLM parametric knowledge.

Systematic benchmark of LLM semantic cache eviction policies (FIFO, LRU, LFU, ARC) shows LFU dominates across settings with <1% margin.

Study compares task-level vs. subtask-level skill induction in LLM agents; finds subtask-level code skills transfer more reliably across domains.

ML classifier for early detection of Solana memecoin rug pulls using liquidity and social signals; blockchain fraud prevention.

DICS: clustering-based approach to reduce candidate split search in decision tree training via data-informed centroid selection.