--- title: Testing AI with an Office Hours Question | daily.dev description: An experienced SQL Server DBA tests seven different AI models (local coding models, DwarfStar/DeepSeek, ChatGPT variants, Claude variants, and Gemini) against... canonical: https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Testing AI with an Office Hours Question | daily.dev og:description: An experienced SQL Server DBA tests seven different AI models (local coding models, DwarfStar/DeepSeek, ChatGPT variants, Claude variants, and Gemini) against... og:url: https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5 og:image: https://api.daily.dev/og/posts/jlsN789Q5.png og:image:alt: Testing AI with an Office Hours Question og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Testing AI with an Office Hours Question **[Brent Ozar](https://daily.dev/sources/brentozar)** · 19 min read · 0 upvotes · 0 comments ## Summary An experienced SQL Server DBA tests seven different AI models (local coding models, DwarfStar/DeepSeek, ChatGPT variants, Claude variants, and Gemini) against a real, nuanced Office Hours question about running DBCC CHECKDB on a synchronous AG secondary for a 25TB database with tempdb full errors. Each answer is graded for technical accuracy from F to B+, revealing that even paid cloud models frequently give confidently wrong or incomplete advice (missing RPO/RTO discussion, misunderstanding filegroup offline behavior, wrong tempdb explanations), while Claude Fable 5 High produced the most accurate response. The conclusion: no single model reliably wins, so continuous testing per-question is necessary rather than committing to one AI answer service, and tools like Nano-GPT and OpenRouter help compare models quickly. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Is it safe to run DBCC CHECKDB on a synchronous secondary in an Availability Group for a 25TB database? It is not inherently dangerous to commits, but CHECKDB is a heavy resource hog on CPU, memory, tempdb, and I/O. On a synchronous secondary, the primary waits for that replica to harden log records before acknowledging commits, so if CHECKDB saturates the secondary's storage or slows log hardening, transaction commits on the primary can be delayed indirectly. Staying on async avoids this risk entirely. _Weighing AG topology tradeoffs against maintenance workloads is easier with daily.dev nearby for SQL Server ops research._ ### How do I avoid tempdb full errors when running full DBCC CHECKDB on a 25TB SQL Server database? Run PHYSICAL_ONLY checks regularly since they only verify page checksums and allocation integrity, using far less tempdb than a full logical check. Reserve full CHECKDB for a restored copy of a backup on a separate server with generously sized, pre-allocated tempdb on fast storage, since a full check at 25TB can need multiple terabytes of tempdb space for internal sort and version-store work. _Developers tuning tempdb sizing for large databases can keep sharpening that judgment via daily.dev._ ### What is DwarfStar (ds4) and what hardware does it need to run DeepSeek locally? DwarfStar, also called ds4, is an open source engine written by Salvatore Sanfilippo (creator of Redis) that runs a heavily quantized version of DeepSeek 4 Flash locally on Macs. It requires at least 96GB of RAM and is aimed at Mac users with that much memory, offering very fast local inference with acceptable quality for many casual questions. _Anyone evaluating local LLM runtimes for Mac hardware can track projects like this through daily.dev._ ## Similar posts on daily.dev - [The Agent Said It Was Done. The Database Disagreed.](https://daily.dev/posts/the-agent-said-it-was-done-the-database-disagreed--th0ihs2vh) · Hugging Face · 2 upvotes · 0 comments - [SQL query generation from natural language](https://daily.dev/posts/sql-query-generation-from-natural-language-onjh4kh6o) · DevBlogs · 1 upvotes · 1 comments - [The Agentic Analytics Benchmark: Measuring model accuracy and efficiency in analytical agents](https://daily.dev/posts/the-agentic-analytics-benchmark-measuring-model-accuracy-and-efficiency-in-analytical-agents-81a3conc5) · ClickHouse · 0 upvotes · 0 comments - [Your Data Model Is the Semantic Layer](https://daily.dev/posts/your-data-model-is-the-semantic-layer-ro8bktzht) · MotherDuck · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#microsoft-sql-server](https://daily.dev/tags/microsoft-sql-server), [#local-ai](https://daily.dev/tags/local-ai) [View this post on daily.dev](https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Testing AI with an Office Hours Question","url":"https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5"},"datePublished":"2026-08-13T13:17:45.790Z","dateModified":"2026-08-13T13:18:16.713Z","description":"An experienced SQL Server DBA tests seven different AI models (local coding models, DwarfStar/DeepSeek, ChatGPT variants, Claude variants, and Gemini) against...","image":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","thumbnailUrl":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","isAccessibleForFree":true,"articleSection":"Brent Ozar","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Brent Ozar","logo":"https://media.daily.dev/image/upload/s--uHhajUhc--/c_limit,w_256/f_auto,q_auto/v1780213426/logos/brentozar?_a=BAMAMiWQ0","url":"https://daily.dev/sources/brentozar"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,microsoft-sql-server,local-ai","timeRequired":"PT19M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Brent Ozar","item":"https://daily.dev/sources/brentozar"},{"@type":"ListItem","position":3,"name":"Testing AI with an Office Hours Question"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/testing-ai-with-an-office-hours-question-jlsn789q5#faq","mainEntity":[{"@type":"Question","name":"Is it safe to run DBCC CHECKDB on a synchronous secondary in an Availability Group for a 25TB database?","acceptedAnswer":{"@type":"Answer","text":"It is not inherently dangerous to commits, but CHECKDB is a heavy resource hog on CPU, memory, tempdb, and I/O. On a synchronous secondary, the primary waits for that replica to harden log records before acknowledging commits, so if CHECKDB saturates the secondary's storage or slows log hardening, transaction commits on the primary can be delayed indirectly. Staying on async avoids this risk entirely. Weighing AG topology tradeoffs against maintenance workloads is easier with daily.dev nearby for SQL Server ops research."}},{"@type":"Question","name":"How do I avoid tempdb full errors when running full DBCC CHECKDB on a 25TB SQL Server database?","acceptedAnswer":{"@type":"Answer","text":"Run PHYSICAL_ONLY checks regularly since they only verify page checksums and allocation integrity, using far less tempdb than a full logical check. Reserve full CHECKDB for a restored copy of a backup on a separate server with generously sized, pre-allocated tempdb on fast storage, since a full check at 25TB can need multiple terabytes of tempdb space for internal sort and version-store work. Developers tuning tempdb sizing for large databases can keep sharpening that judgment via daily.dev."}},{"@type":"Question","name":"What is DwarfStar (ds4) and what hardware does it need to run DeepSeek locally?","acceptedAnswer":{"@type":"Answer","text":"DwarfStar, also called ds4, is an open source engine written by Salvatore Sanfilippo (creator of Redis) that runs a heavily quantized version of DeepSeek 4 Flash locally on Macs. It requires at least 96GB of RAM and is aimed at Mac users with that much memory, offering very fast local inference with acceptable quality for many casual questions. Anyone evaluating local LLM runtimes for Mac hardware can track projects like this through daily.dev."}}]} ```