# GPT-4

Researchers at MIT CSAIL, Google and Northeastern University present InstructMesh, which combines Microsoft's TRELLIS 3D generator with the GPT-4 language model so users can edit 3D designs in natural language and with sliders inside the generative model's latent space; using TRELLIS to recreate popular Thingiverse models, the team found nearly 80 percent had structural flaws, while novices identified and fixed those issues about 90 percent of the time as reviewed by an expert, and they printed objects including a dragon-wrapped mug, butterfly-wing glasses, an octopus-like drink dispenser, a denim-look knee brace and a shrimp-shaped bristle bot.

Researchers at MIT CSAIL, Google and Northeastern University present InstructMesh, which combines Microsoft's TRELLIS 3D generator with the GPT-4 language model so users can edit 3D designs in natural language and with sliders inside the generative model's latent space; using TRELLIS to recreate popular Thingiverse models, the team found nearly 80 percent had structural flaws, while novices identified and fixed those issues about 90 percent of the time as reviewed by an expert, and they printed objects including a dragon-wrapped mug, butterfly-wing glasses, an octopus-like drink dispenser, a denim-look knee brace and a shrimp-shaped bristle bot.

This exploratory study used GPT-4 to generate and iteratively fine-tune an R script for preprocessing and blob identification/counting in adaptive optics flood illumination ophthalmoscopy (AO-FIO) images, debugging it on images from 4 participants (1 healthy individual and 3 patients with Stargardt disease), having another researcher naive to the prior coding check the code for errors using a different test set of images from 4 other participants (1 healthy individual and 3 patients with Stargardt disease), and comparing cone counts from 5 AO image snippets with counts independently recorded by 2 human graders and those from pre-existing AO analysis software, with the authors positioning the script as functional but nonvalidated.

This exploratory study used GPT-4 to generate and iteratively fine-tune an R script for preprocessing and blob identification/counting in adaptive optics flood illumination ophthalmoscopy (AO-FIO) images, debugging it on images from 4 participants (1 healthy individual and 3 patients with Stargardt disease), having another researcher naive to the prior coding check the code for errors using a different test set of images from 4 other participants (1 healthy individual and 3 patients with Stargardt disease), and comparing cone counts from 5 AO image snippets with counts independently recorded by 2 human graders and those from pre-existing AO analysis software, with the authors positioning the script as functional but nonvalidated.