AI tool comparison
Google Gemma 4 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.
Open Source Models
Google Gemma 4
Google's open multimodal models — vision, audio, and text under Apache 2.0
75%
Panel ship
—
Community
Paid
Entry
Google Gemma 4 is the most capable open model family Google has released, and the first to unify text, vision, and audio in a single architecture — all under the Apache 2.0 license. Available in four sizes (E2B, E4B, 26B MoE, 31B Dense), the lineup runs everywhere from smartphones to high-end GPUs and covers 140+ languages with context windows up to 256K. The headline stat: the 31B Dense model benchmarks above models nearly 20x its size in certain evals, making it the sharpest intelligence-per-parameter model in the open-source ecosystem as of its April 2026 release. The multimodal architecture processes documents with OCR, analyzes charts, transcribes speech, and understands video frames from a single model — no pipeline stitching required. For developers and researchers, the Apache 2.0 licensing is the real unlock. Gemma 4 is fully OSI-approved and commercially usable without restriction, building on a community of 400M+ downloads from prior Gemma versions and 100,000+ variants in the wild.
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
“Apache 2.0 on a model that beats GPT-class performance at 31B? Ship it immediately. The MoE 26B variant is already running under 16GB VRAM for me with llama.cpp quantization. The unified multimodal arch saves a ton of pipeline complexity.”
“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.”
“Google's benchmark marketing is getting harder to trust — 'beats 600B rivals' is cherry-picked. The audio modality is notably weaker than Gemini 3.1, and fine-tuning the MoE variant requires infrastructure most teams don't have. Real-world performance lags the headline numbers.”
“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.”
“The 100,000-variant Gemmaverse is a real ecosystem flywheel. Every new Gemma release compresses capability curves downward — things that required cloud APIs last year now run on-device. Gemma 4's audio addition makes it the first truly comprehensive local AI.”
“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.”
“A single model that can read my documents, analyze charts, transcribe my audio notes, and generate code is genuinely transformative for creative production. The Apache license means I can embed it in client deliverables without legal headaches.”
“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.