--- title: Can AI build a jet engine? JARVIS Challenge tests role... description: MIT's JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) had undergraduate students design, fabricate, and test a small jet engine in... canonical: https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering | daily.dev og:description: MIT's JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) had undergraduate students design, fabricate, and test a small jet engine in... og:url: https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty og:image: https://api.daily.dev/og/posts/HRYpoKRtY.png og:image:alt: Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering 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. # Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering **[MIT News](https://daily.dev/sources/mit)** · 9 min read · 0 upvotes · 0 comments ## Summary MIT's JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) had undergraduate students design, fabricate, and test a small jet engine in four weeks using AI as their primary engineering partner. Teams used LLMs like Claude and ChatGPT for trade studies, design comparisons, and knowledge gaps, but encountered hallucinations, sycophancy, and lack of physical intuition. The winning team (811 Crew) was more skeptical of AI and relied on engineering fundamentals, while the fastest-moving team leaned heavily on AI. Key findings: engineering experience amplifies AI value, manufacturing remains the rate-limiting step, vendor relationships can't be replaced by AI searches, and human judgment is irreplaceable for safety-critical physical systems. The challenge suggests AI can compress design-build-test cycles dramatically, but only when engineers have the expertise to direct and verify AI outputs. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can AI tools like ChatGPT and Claude actually help design and build a physical jet engine, not just write code? AI copilots can meaningfully accelerate parts of hardware engineering, such as summarizing textbooks, generating design alternatives, comparing trade-offs, and organizing project work, but they cannot substitute for engineering judgment. In MIT's JARVIS Challenge, students found hallucinations, sycophancy, and a lack of physical understanding undermined confidence once teams moved into detailed CAD design and combustor prototyping, and manufacturing remained the true bottleneck rather than design or analysis. _Engineers weighing how far to trust ai copilots on physical builds can follow real-world experiments like this via daily.dev._ ### Did heavy AI use or deep prior experience matter more for winning MIT's JARVIS jet engine competition? Prior turbomachinery and propulsion experience mattered more than AI usage. Team 811 Crew, which was resistant to using AI and relied on members with backgrounds in mechanical design and gas turbine coursework, won by achieving successful engine start and net thrust, while the team that leaned most heavily on AI for trade studies achieved first ignition but was delayed by vendor issues and ultimately had its rotor seize during testing. _Anyone deciding how much to lean on ai versus fundamentals in engineering work can track findings like this on daily.dev._ ### What is MIT Parley and how was it used in an AI-assisted engineering challenge? MIT Parley is a platform that aggregates frontier large language models through a single interface, launched for use in the JARVIS Challenge. It let competition leads see exactly how students used AI tools, including prompts, cost per prompt, and which specific LLMs were chosen, giving faculty visibility into AI usage patterns across seven student teams building jet engines. _Teams evaluating shared LLM access platforms for engineering projects can keep up with tools like this through daily.dev._ ## Similar posts on daily.dev - [AI-coding tools could be breaking the junior engineer pipeline](https://daily.dev/posts/ai-coding-tools-could-be-breaking-the-junior-engineer-pipeline-zw0im56qf) · LeadDev · 3 upvotes · 3 comments - [Pragmatic by design: Engineering AI for the real world](https://daily.dev/posts/pragmatic-by-design-engineering-ai-for-the-real-world-qqcgjwgbo) · MIT Technology Review · 0 upvotes · 0 comments - [How AI is helping GM build better vehicle software, faster](https://daily.dev/posts/how-ai-is-helping-gm-build-better-vehicle-software-faster-dwcqtarem) · SD Times · 1 upvotes · 0 comments - [A.I. Should Elevate Your Thinking, Not Replace It](https://daily.dev/posts/a-i-should-elevate-your-thinking-not-replace-it-a7si2mcn1) · Hacker News · 0 upvotes · 0 comments - [AI Is Creating a New Type of Software Engineer](https://daily.dev/posts/ai-is-creating-a-new-type-of-software-engineer-jicfi0bpx) · Medium · 0 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding), [#mit](https://daily.dev/tags/mit) [View this post on daily.dev](https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty) ```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":"Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering","url":"https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty"},"datePublished":"2026-07-14T18:06:06.515Z","dateModified":"2026-09-14T06:50:37.904Z","description":"MIT's JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) had undergraduate students design, fabricate, and test a small jet engine in...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/49e1c529d42725c86f28ef0a91fc1129?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/49e1c529d42725c86f28ef0a91fc1129?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"MIT News","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":"MIT News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/881e20a40aa44b12ba4bd27f5c14289d","url":"https://daily.dev/sources/mit"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,llm,ai-coding,mit","timeRequired":"PT9M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"MIT News","item":"https://daily.dev/sources/mit"},{"@type":"ListItem","position":3,"name":"Can AI build a jet engine? JARVIS Challenge tests role of AI copilots in tough-tech engineering"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/can-ai-build-a-jet-engine-jarvis-challenge-tests-role-of-ai-copilots-in-tough-tech-engineering-hrypokrty#faq","mainEntity":[{"@type":"Question","name":"Can AI tools like ChatGPT and Claude actually help design and build a physical jet engine, not just write code?","acceptedAnswer":{"@type":"Answer","text":"AI copilots can meaningfully accelerate parts of hardware engineering, such as summarizing textbooks, generating design alternatives, comparing trade-offs, and organizing project work, but they cannot substitute for engineering judgment. In MIT's JARVIS Challenge, students found hallucinations, sycophancy, and a lack of physical understanding undermined confidence once teams moved into detailed CAD design and combustor prototyping, and manufacturing remained the true bottleneck rather than design or analysis. Engineers weighing how far to trust ai copilots on physical builds can follow real-world experiments like this via daily.dev."}},{"@type":"Question","name":"Did heavy AI use or deep prior experience matter more for winning MIT's JARVIS jet engine competition?","acceptedAnswer":{"@type":"Answer","text":"Prior turbomachinery and propulsion experience mattered more than AI usage. Team 811 Crew, which was resistant to using AI and relied on members with backgrounds in mechanical design and gas turbine coursework, won by achieving successful engine start and net thrust, while the team that leaned most heavily on AI for trade studies achieved first ignition but was delayed by vendor issues and ultimately had its rotor seize during testing. Anyone deciding how much to lean on ai versus fundamentals in engineering work can track findings like this on daily.dev."}},{"@type":"Question","name":"What is MIT Parley and how was it used in an AI-assisted engineering challenge?","acceptedAnswer":{"@type":"Answer","text":"MIT Parley is a platform that aggregates frontier large language models through a single interface, launched for use in the JARVIS Challenge. It let competition leads see exactly how students used AI tools, including prompts, cost per prompt, and which specific LLMs were chosen, giving faculty visibility into AI usage patterns across seven student teams building jet engines. Teams evaluating shared LLM access platforms for engineering projects can keep up with tools like this through daily.dev."}}]} ```