AI SQL

Larch: Learned Query Optimization for Semantic Predicates

Announce Type: new Abstract: With the advent of Large Language Models (LLMs), many database systems introduced semantic operators that enabled analytical queries over unstructured data (e.g. text, images, videos). Semantic operators typically incur high inference costs and latencies making semantic (AI) SQL queries challenging to apply on large scale datasets. At the same time, their semantic nature leads database engines to treat them as black boxes, making AISQL queries difficult to optimize.

BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning

arXiv:2606.02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks. Spider and BIRD established execution-accuracy protocols; G-Eval and RAGAS advanced LLM-based assessment; and recent work such as Spider 2.0, BEAVER, and BIRD-Interact has begun to address enterprise and agentic dimensions. No single...

Data Flow Control: Data Safety Policies for AI Agents

Announce Type: new Abstract: Agents increasingly generate SQL, orchestrate pipelines, and automate data analysis on behalf of users. While recent work improves query correctness, correctness is not safety. A query may be semantically valid yet violate regulatory, privacy, or business constraints that govern how data may be combined and released.

AWS whips out Graviton-powered Redshift instances, claims 7x speed for data warehouse

AWS has introduced Graviton-powered Redshift RG instances, claiming they can accelerate new query workloads by up to seven times. These instances offer significant performance improvements and cost efficiencies compared to previous generations, enabling Redshift to better handle increasing demands from AI agent workloads. The updated engine also allows users to run SQL analytics across both data warehouses and data lakes from a single platform.

pg_durable: Microsoft open sources in-database durable execution

Long-running, fault-tolerant SQL functions for teams that already keep their state in Postgres and want to stop stitching together cron jobs, workers, queues, and status tables to make background work reliable. Define the workflow in SQL, let pg_durable checkpoint each step, and resume after crashes, restarts, or failed steps. Durable execution is now a standard industry pattern, and pg_durable brings it inside Postgres with no extra service infrastructure required.

Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware

arXiv: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 AI Act, which can restrict the use of cloud-based artificial intelligence systems. Locally deployed large language models (LLMs) offer a privacy-preserving alternative, but their suitability for pharmaceutical manufacturing tasks remains underexplored. This study evaluates four open-source LLMs...

Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning

Announce Type: new Abstract: The rapid proliferation of multi-cloud and SaaS platforms has transformed Identity Security Posture Management (ISPM) into a fundamentally cross-vendor challenge: critical misconfigurations and privilege escalation paths increasingly span multiple identity providers, infrastructure layers, and authentication systems never designed to interoperate. Existing evaluations focus on isolated single-platform environments and provide no means to assess whether an AI...

Snowflake to burn $6B on AWS Graviton CPUs and AI accelerators

If Claude Fable stops helping you, you'll never know

I didn't expect to read this in a model card. Fable 5 model card : we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restriction through our safeguards avoids accelerating the actors most willing to violate these terms.

AI, Ashby Engineering, and the future

AI, Ashby Engineering, and the Future 15 minute read Since August 2025, more than half of the new code hitting Ashby’s production systems has been AI-generated, yet customer issues remain broadly stable. More AI-written code. We have a blip in March / April every year; these cyclical patterns aren’t relevant to explain here.