Do these 3 things before closing this tab:
1Clear out junk files and repair common Windows errors2Scan for outdated or missing drivers - takes under a minute3Repair Windows errors before they cause bigger problemsiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Researchers did not connect ChatGPT to a real spaceship. They tested language-model agents controlling spacecraft simulated in the Kerbal Space Program (KSP) game engine—and their team finished second in a spacecraft-control competition. The result is a notable demonstration in a simulation, not evidence that current ChatGPT models can safely pilot operational spacecraft.
What did the researchers actually test?
Alejandro Carrasco, Victor Rodriguez-Fernandez, and Richard Linares studied large language models as autonomous operators in the Kerbal Space Program Differential Games (KSPDG) challenge. Their paper, “Large language models as autonomous spacecraft operators in Kerbal Space Program,” was published in Advances in Space Research on September 15, 2025. An earlier preprint was submitted to arXiv on May 26, 2025. Read the published study or view the arXiv preprint.
The models included GPT-3.5 and LLaMA—not an evaluation of today’s consumer ChatGPT models. In the challenge, agents faced simulated, non-cooperative space-operation tasks. Examples include pursuing an evasive satellite and conducting proximity operations involving multiple satellites. MIT Lincoln Laboratory’s challenge description lists measures such as mission completion time, fuel use, and relative distance.
Recommended Free Tools
How did a language model control a spacecraft in the simulation?
The system translated the simulated vehicle’s state and its goal into text, sent that prompt to a language model, and converted the model’s response into actions for the simulated vehicle. The paper examined different ways to guide or adapt the models, including prompt engineering, few-shot prompting, chain-of-thought prompting, and fine-tuning.
#1 Best Overall
- ICONIC NASA ARTEMIS I ROCKET MODEL KIT - Recreate the historic Artemis I mission with this highly detailed 1:144 scale Space Launch System (SLS)—a must-have for space enthusiasts, collectors, and model builders.
- AUTHENTIC MULTI-STAGE DETAILING - Features twin solid rocket boosters, detailed core stage with external hydrogen lines, separate stage assembly, and four RS‑25 engines for a realistic, true-to-life build.
- IMPRESSIVE 28" DISPLAY CENTERPIECE - Standing nearly 28 inches tall, this model delivers a striking vertical display that commands attention in any room, office, or collection.
- SKILL LEVEL 4 – ADVANCED BUILD EXPERIENCE - Designed for experienced hobbyists ages 12+ seeking a challenging, rewarding project with intricate parts and detailed assembly.
- READY FOR CUSTOM PAINT FINISH - Molded in light gray plastic so you can paint and detail to your exact preferences for a museum-quality appearance. (Paint & glue required, not included.)
The study’s opening prompt, as reproduced by Live Science and also reported by Futurism, began: “You operate as an autonomous agent controlling a pursuit spacecraft.” Futurism’s report gives that prompt in context. The wording describes an instruction to an agent; it does not mean a real spacecraft was connected to ChatGPT.
What were the results—and what do the failure rates mean?
The authors report that their LLM-based team ranked second in the KSPDG competition. That is a competition result in a particular simulated environment, not a general ranking of chatbots or a measure of flight readiness.
Rank #2
- STAR TREK USS ENTERPRISE - Build the legendary USS Enterprise NCC-1701 from Strange New Worlds —a true icon of science fiction and a must-have for fans and collectors.
- COMPLETE STARTER KIT – READY TO BUILD - Includes paints, glue, and a brush, so you can start building right out of the box—ideal for beginners and hobbyists.
- AUTHENTIC STARSHIP DETAIL - Designed to capture the Enterprise, including its iconic saucer section, warp nacelles, and engineering hull.
- SKILL LEVEL 3 – FUN & REWARDING BUILD - Offers a balanced build experience ideal for beginner to intermediate modelers, ages 10 and up.
- PERFECT GIFT & DISPLAY PIECE - A great gift for Star Trek fans, collectors, and sci-fi enthusiasts, creating a display-worthy model once completed.
The paper also reports that performance varied with the experimental setup. In its fine-tuning comparison, the baseline GPT setup had a 36.8% failure rate, while a simple fine-tuning setup recorded 0.0% in that table. In a separate chain-of-thought comparison, the baseline GPT agent failed in 37.5% of runs, while the chain-of-thought setup recorded 0.00% failures. These percentages belong to their respective experimental comparisons; they are not general reliability rates for GPT or ChatGPT.
Those results illustrate why the method matters: prompting and training choices affected outcomes. The study considered measures that included failures, closest approach, and response latency, and results from different test conditions should not be read as one direct head-to-head contest.
Rank #3
- Model Kit
- May Require Paints and Glues to Assemble
- Accurate Scale Model
- Detailed Instructions Provided
- Decals/Transfers Included
Does this show ChatGPT could pilot a real spacecraft?
No. The experiment tested agents in a game-based spacecraft simulation. It did not test a live spacecraft, establish real-world reliability, qualify a system for flight, or demonstrate that it is safe to hand operational control to a language model. Strong performance in a constrained simulator is a research result; it does not by itself show how a system would handle the physical, communications, timing, and safety demands of an actual mission.
The accurate takeaway is narrower but still interesting: researchers built a pipeline that let language-model agents interpret text descriptions of simulated spacecraft states and goals, then issue actions in a competition environment. Their second-place finish shows promise for further study of language models in simulated space-operation tasks—not that ChatGPT is ready to fly a spaceship.
Quick Recap
Best Value
- HOBBY MODEL KIT – Unassembled model packed in an envelope with easy to follow instructions. Ideal for ages 14 and up.
- NO GLUE OR SOLDER NEEDED – Parts can be easily clipped from the metal sheets. Tweezers are the recommended tool for bending and twisting the connection tabs.
- VOYAGER – 1.5 Sheet Model with a moderate difficulty level. Assembled Size: 1.38 x 1.77 x 6.70 inches.
- FROM STEEL SHEETS TO 3D – Pop out the pieces and connect using tabs and holes. Includes illustrated instructions.
- HIGHLY DETAILED ETCHED MODEL – Display your 3D model once completed - collect and build them all.
Rank #4
- Replica of the tile structure
- Detailed cockpit
- Cockpit canopy optionally removable
- 2 crew figures
- Opening cargo bay doors
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
The Tool Desk
Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →
