CompanyAnthropic8 recent entries28 Sept 2026Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL PipelinearXiv:2609.30290v1 Announce Type: new Abstract: Production text-to-SQL pipelines often end with an LLM-as-judge whose agreement with human annotators has never actually been measured. When we checked →30 Sept 2026Data Agent Kit is now GA: Bring Google Data Cloud to any coding agentToday, Google Cloud Data Agent Kit is generally available. Data Agent Kit is a free set of Model Context Protocol (MCP) tools and agent skills that lets the coding agent you already use work directly
CompanyOpenAI8 recent entries9 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→22 Sept 2026Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price warYesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna. It's going to ta→27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→1 Oct 2026Built an SQLite-based memory system for Ollama that doesn't eat all your VRAMWanted to share a project I've been working on to give local Ollama models persistent document memory without needing heavy vector databases. It's called Hillock. The main problem I had with standard →2 Oct 2026Detecting Inconsistencies in Model Specifications with LLM-as-Verifier ReasoningarXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet t→4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info
CompanyGoogle8 recent entries27 Sept 2026Wiki Lint Report — 2026-09-27Automated lint: 17 errors, 59669 warnings, 3 info→30 Sept 2026Spanner Omni, now GA: A distributed, multi-model database that you can deploy anywhereSpanner Omni, the deploy-anywhere version of Spanner, is now generally available, ready to power your most demanding production workloads in your on-premises data center or on other clouds. With Spann→30 Sept 2026Evidence-Guided Schema Normalization for Temporal Tabular ReasoningarXiv:2512.00329v2 Announce Type: replace-cross Abstract: Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose an approach that recasts the task →30 Sept 2026Data Agent Kit is now GA: Bring Google Data Cloud to any coding agentToday, Google Cloud Data Agent Kit is generally available. Data Agent Kit is a free set of Model Context Protocol (MCP) tools and agent skills that lets the coding agent you already use work directly →2 Oct 2026How to implement long-term AI agent memory in AlloyDB and Memorystore for ValkeyEnterprise AI agents need persistent memory to execute complex, multi-day workflows and long-horizon tasks. In this blog, we examine how a 2-tier memory architecture using Memorystore for Valkey for s→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 2026Modernizing Unstructured Data Workflows: Alteryx Live Query meets Google Cloud BigQueryAlteryx One Live Query and Google Cloud BigQuery redefine how enterprises handle complex, unstructured data at scale by reducing reliance on disconnected tools, minimizing data movement, and enabling
CompanyMeta8 recent entries13 Sept 2026Wiki Lint Report — 2026-09-13Automated lint: 12 errors, 54839 warnings, 3 info→15 Sept 2026Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language ModelsarXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach→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→1 Oct 2026GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement LearningarXiv:2609.39869v1 Announce Type: new Abstract: Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic quality when the model's preferred outputs are poor→1 Oct 2026Built an SQLite-based memory system for Ollama that doesn't eat all your VRAMWanted to share a project I've been working on to give local Ollama models persistent document memory without needing heavy vector databases. It's called Hillock. The main problem I had with standard →4 Oct 2026Wiki Lint Report — 2026-10-04Automated lint: 19 errors, 64915 warnings, 3 info→5 Oct 2026From Benchmarks to Production: A Text-to-SQL System for Complex Financial DataarXiv:2610.03524v1 Announce Type: new Abstract: General-purpose Text-to-SQL systems achieve strong performance on academic benchmarks like Spider and BIRD, where schemas are relatively shallow and col
CompanyMistral8 recent entries27 Apr 2026TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code GenerationarXiv:2511.22277v2 Announce Type: replace Abstract: Large language models (LLMs) have shown remarkable ability to generate code, yet their outputs often violate syntactic or semantic constraints when →2 Jun 2026Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade HardwarearXiv:2606.01338v1 Announce Type: new Abstract: Biopharmaceutical manufacturing organizations operate under regulatory frameworks such as FDA guidance, EU Good Manufacturing Practice (GMP), and the EU→9 Jun 2026Initial impressions of Claude Fable 5I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow, →15 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→31 Jul 2026What’s new in AI infrastructure and orchestration this monthAt Google, AI is a soup-to-nuts endeavor. Obviously, we make leading AI models like Gemini and Nano Banana. We incorporate AI into the tools you use every day (think Gmail, BigQuery, AlloyDB, Google C→3 Sept 2026AI-driven development lifecycle using Amazon Bedrock AgentCoreEngineering teams adopting the AI-Driven Development Lifecycle (AI-DLC) often struggle to turn concepts into working code. This post walks through two reference implementations on Amazon Bedrock Agent→11 Sept 2026Detecting hallucinations in local models without eating VRAM: What we learned testing 1.5B to 120B modelsHey everyone, If you run local models via Ollama in production or personal projects, you've probably run into the hallucination problem: how do you know when a model is hallucinating without burning e
CompanyxAI8 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→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→22 Sept 2026Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price warYesterday was Grok 4.7 (pelicans) and MiMo v2.6 Flash/Pro (more pelicans). Today Anthropic released Claude Opus 5.5, and around an hour later OpenAI released GPT-6 Sol and GPT-6 Luna. It's going to ta→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
CompanyDeepSeek8 recent entries11 Sept 2026Detecting hallucinations in local models without eating VRAM: What we learned testing 1.5B to 120B modelsHey everyone, If you run local models via Ollama in production or personal projects, you've probably run into the hallucination problem: how do you know when a model is hallucinating without burning e→12 Sept 2026Nex-N2.5-mini-MLX-4bit on Apple M5 Max — 133.6 tok/s — llm-bench.ioAnother new model dropped in the course of this week that is well deployable on consumer hardware: Nex N2.5 Mini I went with the recommended settings for the best generation quality and ran a few benc→15 Sept 2026Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language ModelsarXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach→27 Sept 2026Worth going from Qwen3.8 27B to flash next or maaybe deepseek v4 flash?I am running qwen3.8 27b on my dual rtx 3090 (fp8 quant, unquantized cache, 129k context) and I think it works decently well with hermes, opencode etc. But! I am tempted by the new models coming out s→4 Oct 2026For dual DGX spark users; GLM 5.3 flash got a 50%+ performance boostFor the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parall→7 Oct 2026We show how you can use the River API to fine-tune open weight models to beat GPT-6 Astra and Claude Opus 5.5 on tasks you care about, with …We show how you can use the River API to fine-tune open weight models to beat GPT-6 Astra and Claude Opus 5.5 on tasks you care about, with less than 1% of the cost! A few years from now most of the L→8 Oct 2026Open sourcing Game Summoner, my prompt to game sitetldr: Open sourced my prompt to game suite: https://github.com/ndamiano/ai-agent-test, it's MIT licensed, and this runs well on my 5090 with 64gb ram, but any model that can handle tool calls can mana→9 Oct 2026Just another purely open-weight models benchmarkLive results, coding benchmarks included, agentic benchmarks included, domains and other classifications filters included. (Spoiler: DeepSeek-V4-Vision-Exp rules, but other models have their rule area
CompanyNVIDIA8 recent entries28 Jul 2026IKS-Instruct: A 24,000-Example Multilingual Dataset for Teaching Language Models Indian Knowledge SystemsarXiv:2607.23322v1 Announce Type: new Abstract: Instruction tuning has become the standard method for adapting large language models to follow human intent, yet existing instruction datasets are domin→28 Jul 2026CHS-SQL: A Text-to-SQL approach based on Confidence-Guided Heuristic Search Schema Linking processarXiv:2607.22624v1 Announce Type: new Abstract: Recently, there have been several works in the Text-to-SQL domain that utilize Small Language Models (SLMs) for training. These approaches achieve perfo→31 Jul 2026What’s new in AI infrastructure and orchestration this monthAt Google, AI is a soup-to-nuts endeavor. Obviously, we make leading AI models like Gemini and Nano Banana. We incorporate AI into the tools you use every day (think Gmail, BigQuery, AlloyDB, Google C→3 Aug 2026'Data center in a Box (on Wheels)' 256Gb VRAM/512Gb RAM AI Server 6-8 Month Operational Review, Stability Write Up, BenchmarksI've been out of these forums for awhile but I figured I would provide a formal update on how this has been going now that it has some operation time under its belt, just to put the information out th→9 Aug 2026DeepSeek v4 Flash 0731 locally on CPUAfter seeing the benchmark results for the full release of DS v4 Flash 0731, I replaced my 2 x 16GB DDR4 ram sticks with 2 x 32GB DDR4 ram sticks to get a max supported of 128 GB RAM, in hope to be ab→3 Sept 2026Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time AnalysisarXiv:2511.12018v2 Announce Type: replace Abstract: Traffic safety analysis at signalized intersections is essential for reducing vehicle and pedestrian collisions, yet traditional crash-based studies→8 Oct 2026Building Reliable Data Analytics Agents: Lessons from the KDD CupThe NVIDIA KGMON team secured second place in the KDD Cup 2026 Data Agents competition by building a constrained harness around a small fixed LLM, unifying heterogeneous data into an SQLite database w→9 Oct 2026Just another purely open-weight models benchmarkLive results, coding benchmarks included, agentic benchmarks included, domains and other classifications filters included. (Spoiler: DeepSeek-V4-Vision-Exp rules, but other models have their rule area