AI tool comparison
Gemini 3.1 Ultra vs Nothing Ever Happens
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
AI Models
Gemini 3.1 Ultra
Google's 2M-token flagship with native multimodal reasoning and sandboxed code execution
75%
Panel ship
—
Community
Paid
Entry
Gemini 3.1 Ultra is Google's most capable model to date, featuring a stable 2 million token context window — enough to process 1,500+ pages of text, hours of video, or an entire large codebase in a single session. Unlike prior Gemini versions that stitched modalities together, 3.1 Ultra was trained from the ground up to reason across text, image, audio, and video simultaneously without transcription intermediaries. It also ships with native sandboxed Python execution: write code, run it, observe the output, revise — all within a single API call. On benchmarks, Gemini 3.1 Ultra shows meaningful gains on ARC-AGI-3, GPQA Diamond, and SWE-Bench Pro, while its long-horizon planning and agentic capabilities are improved over 3.0. The 2M context window is particularly significant for enterprise use cases involving large document sets, video analysis, and extended software projects. Multimodal inputs include chart reading, diagram interpretation, and frame-by-frame video analysis. Available through the Gemini API and Google AI Ultra subscription, Gemini 3.1 Ultra positions Google squarely against OpenAI's GPT-5.5 and Anthropic's Claude Opus 4.7 at the frontier. The sandboxed code execution removes the need for third-party Code Interpreter plugins, and the model's native multimodal design means developers can pass raw audio or video without preprocessing.
AI Experiments
Nothing Ever Happens
An autonomous bot that always bets 'No' on Polymarket doom predictions—and profits
75%
Panel ship
—
Community
Free
Entry
Nothing Ever Happens is a deliberately simple autonomous trading bot that buys "No" contracts on Polymarket prediction markets—specifically targeting non-sports questions about dramatic or catastrophic events. The thesis: humans systematically overestimate the probability that scary predicted events will actually happen. The bot filters markets using LLM-based criteria to exclude sports (where outcomes are more unpredictable) and focuses on the long tail of geopolitical, tech, and social predictions that tend toward "nothing happens." Built by Sterling Crispin (an artist and technologist known for his work on Apple Vision Pro), the project is equal parts satirical commentary and functional trading system. It logs all positions, P&L, and reasoning chains so you can audit its decisions. The name references an internet phrase mocking catastrophist news cycles—"nothing ever happens" is the skeptic's rebuttal to perpetual crisis framing. The HN post hit 370 points and 180+ comments in a few hours, sparking genuine debate about whether this is a sound strategy, a fun toy, or a comment on prediction market epistemology. Real-world results aren't yet published, but the idea of using an LLM as a "doom filter" for prediction markets is novel enough to be worth watching.
Reviewer scorecard
“The native sandboxed Python execution is a major unlock. Being able to write, run, and iterate on code within the same API call — without stitching together a Code Interpreter plugin — simplifies a lot of agentic workflows. The 2M context window makes whole-repo analysis actually practical rather than theoretically possible.”
“Clean architecture, good logging, and a legitimately interesting hypothesis about prediction market psychology. The LLM filtering layer for 'doom vs. non-doom' questions is a smart abstraction. Even if the strategy underperforms, the codebase is a solid template for automated Polymarket bots.”
“We've seen frontier model releases every few months and the benchmark improvements are getting smaller. 'Trained natively multimodal' was also claimed for Gemini 1.5 and 2.0. The 2M context window is impressive but most applications don't need it, and the cost at that scale is non-trivial. GPT-5.5 and Claude Opus 4.7 are both serious competition.”
“The strategy looks good in backtests but Polymarket's liquidity is thin and arbitrageurs will price this edge away quickly once it's well-known. Also: 'nothing ever happens' is survivorship bias dressed as strategy—the times something DOES happen, you're wiped out. Don't put meaningful capital here.”
“A 2M context window that natively understands video is a qualitative leap for enterprise AI. Imagine analyzing an entire quarter of earnings calls, legal discovery sets, or a full feature film for post-production — all in one shot. The sandboxed execution loop is the building block for fully autonomous data science agents.”
“Autonomous agents that trade prediction markets based on LLM-assessed epistemic calibration is a genuinely new thing. If this works at scale, it could actually make prediction markets more accurate by algorithmically correcting for human doom-bias. That's a more interesting outcome than any individual P&L.”
“Native audio and video understanding without transcription intermediaries is huge for content workflows. Passing raw video directly and getting intelligent analysis — not just captions — opens up automated editing assistants, content QA, and creative research tools that weren't practical before. Google finally has a model worth building creative tools on.”
“Sterling Crispin making a 'nothing ever happens' bot is peak art-meets-tech. It's a functional piece of commentary on the anxiety economy—we're so primed for crisis that prediction markets misprice normalcy. The aesthetic of it is as interesting as the trading logic.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.