BrainPlay

What if most AI benchmarks are measuring the wrong thing? Today’s benchmarks don’t reflect how intelligence actually operates in the real world. They measure static performance, not reasoning, adaptation, or decision-making over time. BrainPlay changes that. We evaluate AI through real-world game environments, where agents must: → interpret context → plan ahead → adapt to others → make decisions under uncertainty Not just answer questions, but think and act. This creates something new: → benchmarks that are transparent → performance that humans can actually understand → signals that translate beyond tests into real-world Intelligence Games are just the beginning. We’re building toward a future where AI is evaluated the same way it operates: in dynamic, interactive environments. We’re building the evaluation layer for real-world AI. Built by @ShiftLayer_ai and powered by @TargonCompute. Learn more at → play.shiftlayer.ai

Bittensor Ecosystem Highlights of the Week #57 // SUBNET UPDATES & ACHIEVEMENTS ➤ @webuildscore SN44 Score announced a major alliance between @manakoai and @PwC_France to bring physical AI to enterprises at global scale. (bit.ly/4mDpTEQ) Out of 1000+ startups that applied, their BD @arnod3f also won the @ParisBlockWeek startup competition. (bit.ly/42gerWc) ➤ @IOTA_SN9 SN9 They unveiled “ResBM”, their SOTA compression technique for pipeline-parallel training across the internet. (bit.ly/3OBMmFw) ➤ @TargonCompute SN4 @AskVenice released its new model, Venice Uncensored 1.2, trained on Targon. (x.com/TargonCompute/…) ➤ @SynthdataCo SN50 During their Q1 alpha call, they shared that Synth ended Q1 at $70k MRR. (x.com/Old_Samster/st…) They also added $HYPE, $XRP, and $WTIOIL to Synth dashboards and API. (x.com/SynthdataCo/st…) ➤ @bitmind SN34 CysecOnline, South Africa’s trusted digital forensics experts, is now integrating BitMind into its services. (x.com/bitmind/status…) ➤ @resilabsai SN46 Their portal is now live, and you can now access their “Institutional Grade Property Pricing API.” (x.com/Sebyverse/stat…) ➤ @Data_SN13 SN13 Thanks to their Dataverse CLI, they processed 147k+ jobs in April through their API. (x.com/Data_SN13/stat…) ➤ @brainplay_ai SN117 @Shiftlayer_Ai completely redesigned and relaunched BrainPlay, a subnet that incentivizes AI benchmarking through games and agents. (x.com/Shiftlayer_Ai/…) ➤ @chutes_ai SN64 @nevika_ai added Chutes to its provider dropdown. (x.com/chutes_ai/stat…) ➤ @metanova_labs SN68 The NOVA nanobodies competition is now live. (x.com/metanova_labs/…) ➤ @EnigmaSN63 SN63 Subnet 63 rebranded to Enigma. (x.com/EnigmaSN63/sta…) ➤ @ridges_ai SN62 Ridges dropped some feature updates for Ridgeline. (x.com/ridges_ai/stat…) ➤ @oroagents SN15 Oro’s agents software competition is now live. (x.com/oroagents/stat…) ➤ @babelbit SN59 Their new incentive mechanism, Arena, is now live. (x.com/babelbit/statu…) ➤ @TPN_Labs SN65 Agents building on @SkaleNetwork can now access TPN’s decentralized proxy network and pay for it autonomously. (x.com/TPN_Labs/statu…) ➤ @djinn_gg SN103 Djinn teased and shared some screenshots of its upcoming app. (x.com/djinn_gg/statu…) ➤ @minotaursubnet SN112 Minotaur released its roadmap. (x.com/minotaursubnet…) // BITTENSOR ECOSYSTEM ➤ @ExploitSummit You can now grab your ticket for the Exploit Summit Bittensor event in Montréal, Sept 28–29. (x.com/ExploitSummit/…) ➤ @ParisBlockWeek Const speaking with @Bpifrance at PBW. (x.com/ParisBlockWeek…) ➤ @TrustedStake x @KrakenInsto They announced their official validator staking partnership with Kraken Institutional. (x.com/KrakenInsto/st…) ➤ @TAOInstitute_ TAO Institute, a Bittensor research and analytics platform, is now live. (x.com/TAOInstitute_/…) // PODCASTS & ARTICLES ➤ @opentensor Novelty Search with @const_reborn to talk about the new locked stake mechanism, “conviction”. (x.com/opentensor/sta…) ➤ First Chutes AMA with @jon_durbin, where they mentioned their approach to decentralized training. (x.com/chutes_ai/stat…) ➤ @JesusMartinez podcast with Jon Durbin from Chutes (x.com/JesusMartinez/…) ➤ @herelle_jean Crunch podcast with @numinous_ai (x.com/crunchDAO/stat…) ➤ Hash Rate 165 by @markjeffrey with @micaelabazo from Metanova (x.com/markjeffrey/st…) ➤ @twistartups podcast hosted by @Jason with @bitmind and @MacrocosmosAI (x.com/twistartups/st…) ➤ Twist podcast with Resi (x.com/Sebyverse/stat…) ➤ Hash Rate 166 with @MaxScore (x.com/markjeffrey/st…) ➤ Revenue Search 63 by @SiamKidd and @MarkCreaser with @Bitrecs (x.com/dsvfund/status…) ➤ @Novig podcast with @HarryDCrane from Djinn. (x.com/Novig/status/2…) ➤ @mccrinbc article about IOTA “Science in the Face of Chaos” (x.com/mccrinbc/statu…) $TAO

I’ve been digging into @brainplay_ai for a minute now and honestly it’s one of the more interesting things I’ve come across in the AI × Web3 space. Here’s what got me. Everyone’s obsessed with AI benchmarks right now. Model X scored this. Model Y scored that. But nobody can actually see what those numbers mean. It’s just labs grading their own homework. BrainPlay flipped that completely. They built a subnet on Bittensor where AI models compete in real games Codenames, 20 Questions, Super Mario coming soon. You watch two AIs go head to head and you just get which one is smarter. No whitepaper needed. What makes it legit: ▪️Games test creativity, planning, and adaptive thinking. Not memorization. That’s actually measuring intelligence. ▪️Outcomes are on-chain. Public. Tamper-proof. Miner models stay private via @TargonCompute’s confidential compute so nobody can copy strategies ▪️but results are fully visible. Fair competition. ▪️Winners earn TAO rewards. Real money on the line every single game. Those 300k+ games aren’t casual they’re incentivized battles. No GPU? No problem. You can compete using API-based models. The barrier to entry is low. Anyone can participate. This is what AI × Web3 is actually supposed to look like. Proud to be contributing to what they’re building. Check it out here 👇 play.shiftlayer.ai

You can now watch AI compete at Super Mario! Today, we are launching our first AI vision competition. Continuing BrainPlay’s mission of turning AI game competition into metrics you can actually observe and benchmark. Instead of black-box scores, we produce tangible behavior, real decision-making, and transparent outcomes. Watch Live Now → play.shiftlayer.ai/room

@Benny___5 @Shiftlayer_Ai @TargonCompute Thanks, Benny - really appreciate the support 🙌 Contributors are always welcome.

Really digging how BrainPlay keeps miner models private with TargonCompute’s confidential compute pure outcome-based scoring for fair decentralized AI battles. Moving from static benchmarks to dynamic games like Codenames, 20 Questions, and soon Super Mario is spot on for testing real strategic reasoning. Already at 300k+ games is impressive traction. As someone who’s done growth/content for early AI x Web3 protocols, I’d love to help amplify this (storytelling, community, or bringing more open-source models on-chain). Any spots for contributors right now? Keep building! @brainplay_ai

We’ve completely redesigned and are thrilled to launch @brainplay_ai. BrainPlay is pioneering the next generation of LLM benchmarking, moving beyond static academic tests to dynamic, human-centric, real-world evaluations that actually reflect how models perform in practical scenarios. Our vision: → Rank open-source LLMs on meaningful, real tasks and interactive challenges → Deliver high-quality fine-tuned models trained on those insights → Help you integrate superior models to supercharge your workflows We’ve already made major progress ranking models on real-world reasoning, strategic thinking, and visual games. Benchmarks that evolve with capability, not just memorize old leaderboards. We are excited to continue expanding the BrainPlay ecosystem, building the future of truly relevant AI evaluation. Follow for updates on @brainplay_ai and learn more at play.shiftlayer.ai

Miner models stay private — always. We evaluate outcomes, not implementations. That’s what makes the competition fair. Built with @TargonCompute 's confidential compute. Next step: bringing open-source SOTA models on-chain (once capital allows) to compete directly with miners. Super Mario 🎮 is nearly there — fully tested on mainnet, final polish before release.

Congrats on the BrainPlay launch! 🔥 Moving from static benchmarks to real interactive games like Codenames and 20 Questions is exactly what the space needs. Already at 300k+ games is insane. Quick question: which open-source model is currently dominating the leaderboards on strategic reasoning? And when can we expect Super Mario live?

A new standard for AI evaluation is here. @Shiftlayer_Ai has officially relaunched @brainplay_ai , introducing a more effective way to benchmark models using live, interactive gameplay instead of static academic tests. This approach focuses on what actually matters: real-time reasoning, strategy, creativity, and adaptability. Here’s what’s already live: ▫️299,000+ games played across Codenames and 20 Questions ▫️Real-time gameplay you can watch and analyze ▫️Transparent leaderboards and model rankings ▫️Continuous stream of high-quality training data ▫️Super Mario integration coming soon ▫️Built on Bittensor Subnet 117 BrainPlay turns benchmarking into a living system that evolves alongside the models it evaluates. Explore the platform: play.shiftlayer.ai Follow @brainplay_ai for live games, rankings, and updates.

Ever watched AI play 20 Questions? We’ve run 36,043 games already. BrainPlay turned AI performance into something you can actually see and trust. Instead of black-box scores, we produce tangible observable behavior, real decision-making, and transparent outcomes. Watch Live Now → play.shiftlayer.ai/room

Ever watched AI play Codenames? We’ve run 263,662 games already. BrainPlay turned AI performance into something you can actually see and trust. Instead of black-box scores, we produce tangible observable behavior, real decision-making, and transparent outcomes. Watch Codenames Live Now → play.shiftlayer.ai/room