TechniqueRLHF / Alignment8 recent entries19 Aug 2026A multi-view contrastive learning framework for spatial embeddings in risk modellingarXiv:2511.17954v2 Announce Type: replace-cross Abstract: Incorporating spatial information, particularly when related to climate, weather, and demographic factors, is crucial for improving underwriti→9 Sept 2026Wiki Lint Report — 2026-09-09Automated lint: 12 errors, 53990 warnings, 3 info→13 Sept 2026Wiki Lint Report — 2026-09-13Automated lint: 12 errors, 54839 warnings, 3 info
TechniqueRAG8 recent entries15 Jul 2026Wiki Lint Report — 2026-07-15Automated lint: 26 errors, 6728 warnings, 3 info→19 Jul 2026Wiki Lint Report — 2026-07-19Automated lint: 20 errors, 8743 warnings, 3 info→4 Sept 2026Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability FloorarXiv:2609.03221v1 Announce Type: new Abstract: Counterfactual audits are the standard tool for checking whether a clinical agent treats demographically distinct but clinically identical patients diff→9 Sept 2026Wiki Lint Report — 2026-09-09Automated lint: 12 errors, 53990 warnings, 3 info→13 Sept 2026Wiki Lint Report — 2026-09-13Automated lint: 12 errors, 54839 warnings, 3 info→20 Sept 2026Wiki Lint Report — 2026-09-20Automated lint: 14 errors, 54840 warnings, 3 info→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info
TechniqueAgents8 recent entries3 Oct 2026Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and fin…Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for real world docs (ins→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→6 Oct 2026Analysis: insurers brace for multimillion-dollar claims caused by rogue AI agents, amid concern that Sam Altman, Dario Amodei, and others could be held liable (Lee Harris/Financial Times)Lee Harris / Financial Times: Analysis: insurers brace for multimillion-dollar claims caused by rogue AI agents, amid concern that Sam Altman, Dario Amodei, and others could be held liable — Insurers →6 Oct 2026A local 27B model reads my lease and finds a leak in my bills | Row-Bot + qwen3.8 on OllamaRow-Bot 5.0 with qwen3.8:27b in Ollama, on my own GPU. No API keys, no cloud. Gave it a year of bills, a tenancy agreement, an insurance policy and a rent increase letter (all made up). It spotted a l→8 Oct 2026Welcome to Gemini at Work 2026: Introducing the Gemini agentEditor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your →9 Oct 2026ThinkingBox: Solving an agent task once vs. solving it 20/20: 507 stateful workflows graded on terminal database state [R]Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel→9 Oct 2026H2O-Lightning-4B: Apache-2.0 4B Decision model, official #1 open model on JevBench (above Jev)Disclosure: I work at H2O.ai. We released H2O-Lightning-4B, an open-weight (Apache-2.0) model for the 'decisions API' style of inference that Jev made popular: you send a state plus typed questions (p→9 Oct 2026Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's o…Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su
TechniqueFine-tuning8 recent entries11 Aug 2026Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure RerankingarXiv:2608.09650v1 Announce Type: cross Abstract: Reranking medical procedures against patient queries is a critical component of health insurance information retrieval, complicated by a substantial l→25 Aug 2026Now introducing Gemini Enterprise for Financial ServicesProtecting capital in today's markets requires immense speed and precision. A financial analyst preparing a deal memo works across licensed market data, internal models, and confidential client files.→9 Sept 2026Wiki Lint Report — 2026-09-09Automated lint: 12 errors, 53990 warnings, 3 info→13 Sept 2026Wiki Lint Report — 2026-09-13Automated lint: 12 errors, 54839 warnings, 3 info→20 Sept 2026Wiki Lint Report — 2026-09-20Automated lint: 14 errors, 54840 warnings, 3 info→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→9 Oct 2026H2O-Lightning-4B: Apache-2.0 4B Decision model, official #1 open model on JevBench (above Jev)Disclosure: I work at H2O.ai. We released H2O-Lightning-4B, an open-weight (Apache-2.0) model for the 'decisions API' style of inference that Jev made popular: you send a state plus typed questions (p
TechniqueMultimodal8 recent entries13 Sept 2026Wiki Lint Report — 2026-09-13Automated lint: 12 errors, 54839 warnings, 3 info→20 Sept 2026Wiki Lint Report — 2026-09-20Automated lint: 14 errors, 54840 warnings, 3 info→24 Sept 2026Power your agents: Gemini 3.8 Live with Live Avatar is now generally availableFollowing our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enter→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→1 Oct 2026From Wrecks to Wisdom: Recovering Crash Mechanics from Real-World Multi-View PhotosarXiv:2609.39486v1 Announce Type: new Abstract: Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operatio→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→6 Oct 2026Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation TransferarXiv:2610.04946v1 Announce Type: new Abstract: Cross-system transfer of longitudinal Electronic Health Record (EHR) representations is challenging because clinical coding, patient populations, and he→8 Oct 2026Welcome to Gemini at Work 2026: Introducing the Gemini agentEditor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your
TechniqueSafety8 recent entries23 Sept 2026A Practical Guide on Graphical Model ValidationarXiv:2609.26445v1 Announce Type: cross Abstract: This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like ca→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→28 Sept 2026Insurance Reserve Intelligence PlatformarXiv:2609.30765v1 Announce Type: new Abstract: Insurance reserve estimation is a fundamental actuarial task supporting premium pricing, solvency assessment, financial reporting, capital planning, and→1 Oct 2026From Wrecks to Wisdom: Recovering Crash Mechanics from Real-World Multi-View PhotosarXiv:2609.39486v1 Announce Type: new Abstract: Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operatio→2 Oct 2026Beyond Demographic Balance: Multi-Metric and Intersectional Evaluation of Fairness in MIMIC-IV Mortality PredictionarXiv:2610.01645v1 Announce Type: new Abstract: Fairness conclusions in clinical prediction can depend strongly on both the metrics reported and the demographic resolution at which performance is eval→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→8 Oct 2026Welcome to Gemini at Work 2026: Introducing the Gemini agentEditor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your →9 Oct 2026Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's o…Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su