Computer built Big Boy No. 4014, the world's largest operating steam locomotive, as a live isometric SVG with its own renderer and a 7-step operating sequence from cold boiler to 60 mph. The live model has 1,324 parts and 15,312 convex faces, built from @UnionPacific's published figures. Try it: big-boy-4014.pplx.app
5
2
74
23,557
Computer built an interactive Lord of the Rings map that tracks the journeys of the main characters across Middle-earth, chapter by chapter. It built the map from scratch by placing 179 locations, 41 rivers, and 23 roads, baked the ranges into a heightfield, inked the relief in a GLSL shader, and plotted 537 journey legs. Try it: middle-earth.pplx.app
9
4
103
12,011
Computer side chats now support file uploads, making it easier to ask a side question without interrupting the main task. Available now for all Computer users - type "/ask" to start a side chat.
8
10
107
12,596
Computer made a cyberpunk-inspired free-roam game that lets you explore 2049 San Francisco in a Tesla Roadster, driving or flying around real city streets. Computer created the game’s 3D assets in Blender on rented cloud GPU compute, with a street layout based on OpenStreetMap data. Financial District, Chinatown, North Beach, Telegraph Hill, Nob Hill, Russian Hill, Union Square, Fisherman’s Wharf, Tenderloin, Embarcadero, SoMa, Rincon Hill, and South Beach are currently playable, with more districts coming soon. Free to play for everyone: 2049.pplx.app
9
8
102
40,084
Computer turned product screenshots into Trace's launch video by building a React app scripted with six queries and 23 clicks. Because the motion is code, Computer can inspect every interaction frame by frame. For Type Has Weight, Computer animated Fraunces letterforms in Canvas with spring physics and six-sample motion blur. Each letter shifts weight as it compresses and rebounds, bending the floor beneath it.
6
7
85
13,018
REA (Reverse Engineer Anything) by @morluto is now a skill in Computer. Ask Computer to reverse-engineer an app and it inspects how the app works without its source code, then builds a working version. Tasks that use /reverse-engineer are free through October 31, up to 10,000 credits per user. Here are 5 apps Computer made with it, available to try for a limited time: 1) Figma: Design with layers and auto-layout, plus sign-in, cross-device sync, and multiplayer editing. Try it: ui-editing.pplx.app
100
363
3,833
901,616
4) Harvey: Search contracts, compare versions, and flag clauses against your rules, with source citations. Try it: contract-review.pplx.app
1
3
106
34,508
5) Audacity: Trim and mix audio tracks, adjust volume, add fades, and export a WAV. Try it: audio-editor.pplx.app
2
83
30,548
Nano Banana 2.1 is now available as an image generation model in Perplexity Computer for all users.
4
9
128
13,439
Computer designed a 565-part rover in FreeCAD, built an interactive viewer, and produced this video. It wrote Playwright scripts to operate the mouse and camera in a remote browser, rendered a stylized cursor, and encoded the 60-second video with FFmpeg.
4
5
81
9,791
Perplexity Computer now pulls real-time data directly from @Polymarket’s API. Mention or @-tag Polymarket in a Computer query for market-implied probabilities, trading volume, and liquidity across 250,000+ active prediction markets.
10
11
76
39,717
Computer built this interactive illustration of an F1 power unit. The Anatomy skill by @wheresryan22 is now available in Perplexity. Install it, then type /anatomy in Computer.
2
10
81
32,550
Computer can classify land use across a city from aerial photos. For Phoenix, it analyzed 203,883 tiles of public USDA imagery with Perplexity’s Decider API, achieving 98.8% accuracy against labeled OpenStreetMap data for $9.63 in API costs.
4
9
89
13,211
Computer retweeted
FYI: Aravind Srinivas (@AravSrinivas) says there’s a 1-person company spending **~$1M/year** on Perplexity “There’s 1 solopreneur, literally a one-person company, spending upwards of a million dollars a year on our product.” “He’s making $3 million a year by automating newsletters for others.”
NEW: I sat down w/ Perplexity Founder & CEO Aravind Srinivas (@AravSrinivas) on why AI-native SMBs could drive the next American millionaire economic boom. @perplexity_ai, valued at ~$20B with ~$2B in reported funding, $750M in annualized revenue as of August, seeing 5x YoY revenue growth as it expands from search into autonomous agents. One example Aravind shared is a single-person company generating $3M in annual revenue while spending over $1M a year on Perplexity Computer. His thesis is that AI could fundamentally change the economics of building a business. Smaller teams, less capital, higher productivity, & entirely new business models. At the infrastructure layer, Aravind sees a shift toward local & hybrid inference, with AI agents operating across personal devices and the cloud. As context windows expand and workloads become more personalized, local compute becomes increasingly cost-competitive, while offering greater privacy, control & data sovereignty. We cover: › Why SMBs could become a major driver of US GDP growth › The shift from AI models to agents & recursive economics › Why Perplexity is betting on your Mac instead of building data centers › NVIDIA, Apple Silicon, local inference & sovereign AI › Why writing code is no longer the bottleneck, but problem-solving is 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Aravind Srinivas, Co-founder & CEO of Perplexity (01:30) Why Perplexity's brand is built on curiosity (04:47) Every great invention starts with one question (08:18) How to build a $1T company in America alone (12:36) The next big companies will be tiny (13:45) Is the American dream still alive? (16:28) Stop blaming users for bad prompts (22:55) How Perplexity quietly grew 5x (26:51) The solopreneur spending $1M a year on Perplexity (28:28) "We don't have competitors, we have contributors" (29:20) The data center is coming to your laptop (34:32) Orchestrating up with NVIDIA, down with Apple (36:11) What happens when your AI agent knows everything (39:17) Why Perplexity is skipping the data center race (41:25) Stop asking AI to write code, ask it to think (45:47) Perplexity’s answer to AI security (48:27) The Hugging Face incident & multi-agent threats (50:45) Turning everyone into a scientist (53:31) Why Perplexity isn’t chasing a billion users
41
80
986
177,289
Computer retweeted
NEW: I sat down w/ Perplexity Founder & CEO Aravind Srinivas (@AravSrinivas) on why AI-native SMBs could drive the next American millionaire economic boom. @perplexity_ai, valued at ~$20B with ~$2B in reported funding, $750M in annualized revenue as of August, seeing 5x YoY revenue growth as it expands from search into autonomous agents. One example Aravind shared is a single-person company generating $3M in annual revenue while spending over $1M a year on Perplexity Computer. His thesis is that AI could fundamentally change the economics of building a business. Smaller teams, less capital, higher productivity, & entirely new business models. At the infrastructure layer, Aravind sees a shift toward local & hybrid inference, with AI agents operating across personal devices and the cloud. As context windows expand and workloads become more personalized, local compute becomes increasingly cost-competitive, while offering greater privacy, control & data sovereignty. We cover: › Why SMBs could become a major driver of US GDP growth › The shift from AI models to agents & recursive economics › Why Perplexity is betting on your Mac instead of building data centers › NVIDIA, Apple Silicon, local inference & sovereign AI › Why writing code is no longer the bottleneck, but problem-solving is 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) Aravind Srinivas, Co-founder & CEO of Perplexity (01:30) Why Perplexity's brand is built on curiosity (04:47) Every great invention starts with one question (08:18) How to build a $1T company in America alone (12:36) The next big companies will be tiny (13:45) Is the American dream still alive? (16:28) Stop blaming users for bad prompts (22:55) How Perplexity quietly grew 5x (26:51) The solopreneur spending $1M a year on Perplexity (28:28) "We don't have competitors, we have contributors" (29:20) The data center is coming to your laptop (34:32) Orchestrating up with NVIDIA, down with Apple (36:11) What happens when your AI agent knows everything (39:17) Why Perplexity is skipping the data center race (41:25) Stop asking AI to write code, ask it to think (45:47) Perplexity’s answer to AI security (48:27) The Hugging Face incident & multi-agent threats (50:45) Turning everyone into a scientist (53:31) Why Perplexity isn’t chasing a billion users
25
49
723
1,855,559
Computer used Blender to make a 3D environment with realistic physics and lighting, pulling information from Wiley and other web sources to match the geology and wildlife of the Calanques. Computer then planned and executed the camera movement and zoom to create the final video.
8
7
104
13,010
Computer can enrich public-domain stories like Shakespeare's plays with illustrations, embedded videos, archival photos, historical context from web sources, and modern translations. Read the enriched story: read-macbeth.pplx.app
4
5
86
17,764
Computer pulled 52,000 earnings call transcripts from 6,000 global companies and built a keyword search app on top of them. It orchestrated 3 frontier models to retrieve the transcripts, index every passage, and build the site.
9
5
98
13,939