Reinforcement Learning as a Service for optimizing agent trajectories powered by Bittensor.

Joined February 2026
2 Photos and videos
Pinned Tweet
**TrajectoryRL Update** A quick recap of what shipped on SN11 recently. — **What TrajectoryRL is** TrajectoryRL ships out-of-the-box SOTA agents on small open-source LLMs. SN11 on Bittensor is the open market that pays for the agent scaffolds that move the quality / cost frontier. First vertical: autonomous coding on `qwen/qwen3.5-35b-a3b`. Miners ship prompts with harness; the network pays for the ones that move the frontier. **Introducing Terminal-Bench** In a recent update, we introduced **Terminal-Bench** — `trajrl-bench` leverages part of its scenarios for our eval harness. That means miners optimize against real, public agent tasks rather than a benchmark we invented in-house. Every scenario has public provenance, and SN11's SOTA claims sit on top of established agent-evaluation work. github.com/harbor-framework/… — **Challenger / Winner mode — new incentive mechanism** The previous mechanism ran 24-hour epochs that re-evaluated every miner from scratch. We've moved to **Challenger / Winner mode**: one challenger per epoch, evaluated head-to-head against the seated winner. The seat only changes when a challenger qualifies and beats the seated score by ≥ δ. cleaner signal, Faster epochs and faster finalized emissions. — Learned a lot from Distill along the way — shout out to @const_reborn Live at trajrl.com/live. #Bittensor #SN11 #TrajectoryRL
3
8
34
16,133
The next era of SN11: bring your own model. Season 1 proved the skill competition. SKILL.md packs took a stock 35B open model from "reads the task and gives up" to near-ceiling on real terminal tasks. Now we're opening the next lever: miners will submit finetuned models, not just skill packs.
4
6
54
4,376
A submission becomes a (SKILL.md, model) pair. Models are SFT finetunes of Qwen3.6-35B-A3B, registered on our inference subnet (separate announcement coming) and served with verified inference: the server cryptographically proves it ran the claimed weights. Any miner can build packs on any registered model. When a submission wins, the model author earns additional SN11 emissions on top of what the pack author earns. Pack rewards stay whole. Build the best model, and every pack that wins on it pays you.
1
11
3,802
Want to finetune but lack hardware? We operate our own GPU clusters and will provide servers to committed finetuners. Reach out in Discord. The goal: the SOTA agentic model for a domain, one domain at a time. Next up: DevOps, the agent that operates machines.
6
629
TrajectoryRL retweeted
Jun 2
Proof of talk
1
1
15
978
Continual Learning, that's also our conviction, we'll train our own coding model with our daily 1000 agent trajectories.
Today, @MichaelElabd, @QuantumArjun, and I are excited to announce Trajectory. We are a research lab and product company building the platform for Continual Learning. Our platform unlocks the signal already sitting in product usage, so companies can continuously post-train large-scale agentic models that outperform the frontier. @trajectorylabs We’ve raised $15M from @Conviction, @BessemerVP, @radicalvcfund, @jeffdean, @drfeifei and more. We’re partnering with some of the best AI-native companies: @ClayRunHQ @Harvey, @DecagonAI, @mercor_ai, @RogoAI to power their agentic systems, some of which we are already in production with. We’ve brought together a world class research team from DeepMind, OpenAI, Apple, Meta Superintelligence, Amazon AGI, Scale AI, and an elite product team from Stripe and Figma. AI will never again start on day one. Every correction, every retry, every edit will make products smarter. This is Continual Learning.
5
41
6,054
"Agent = Model Harness." Spot on. It's also the bet behind TrajectoryRL — a Bittensor subnet that benchmarks harness quality(prompts, tools, sandbox, loop). Once you measure agents this way, the "which model is smartest" debate gets a lot less interesting. Harness gap is the real capability gap.
2
5
23
2,286
TrajectoryRL retweeted
May 1
it's crazy to think open-source small LLMs are only 1-1.5 years behind frontier. imagine running GPT-5.5 or Opus 4.7 on your gaming PC a year from now. Purely local inference.
2
2
23
1,887
TrajectoryRL retweeted
Subnet 11 on Bittensor has 3 olympiads from China btw
Apr 29
What do the smartest kids in the world do when they grow up? I did the largest study of ~18,000 International Olympiad medalists (IMO, IOI and IPhO) over the last 25yrs, arguably the sharpest analytical minds of the world in high school, to see where they ended up and traced ~50% of them. Founders of ~20 unicorns and ~7 decacorns and ~10 billionaires: OpenAI, Cursor, Stripe, Databricks, Perplexity, Ethereum, Cognition, Hyperliquid, Fireworks, Modal, Quora, Parallel, Cartesia, Wispr Most kids went to MIT, a whopping 12% of them, followed by Cambridge (7%) and Sharif (3%)! The career paths they chose (of those who graduated) were: — 36% Academia (professors) — 26% Other — 22% in Software / Tech — 12% in Quant / Finance — 5% Founders! The biggest employer was Google, by far, at 6%. Others interesting tidbits were: — 47 of them work at Jane Street (#3) — 38 at OpenAI (#5) — 15 at Anthropic — 8 at Cognition — 6 at Isomorphic Labs Olympiaders were 1500x more likely to be billionaires and 4000x more likely to be unicorn founders than the average person!
13
18
273
36,603
Checkout trajrl.com, we distill skills and trajectories for agents by leveraging Bittensor’s collective intelligence.
I like blockchain tech quite a bit because it extends open source to open source state, a genuine/exciting innovation in computing paradigms. I'm just sad and struggle to get over it coming packaged with so much braindead bs (get rich quick pumps/dumps/scams/spams/memes etc.). Ew
2
5
31
2,270
TrajectoryRL retweeted
If you haven’t yet please go check out @macrozack aura farming and @TrajectoryRL’s vision on @twistartups 👀
SpaceX’s AI arm is partnering with coding startup Cursor in a deal worth no less than $10 billion and as much as $60 billion. Can the pair topple the rising Anthropic-OpenAI AI coding axis? A lot of money is being bet that the answer is yes. Next up, @lons and @alex invited the @bitstarterAI team on the show to discuss their work to help kickstart new Bittensor subnets. The dynamic duo had a new program to announce, so make sure to tune into their pitch if you have dreams of launching your own subnet. Then we brought @TrajectoryRL onto the pod, a Bittensor subnet that holds competitions to improve agent skills. Yes, the markdown files that everyone who uses OpenClaw swears by. Hit play, let’s have some fun! 2:27 Plaud: If your work depends on conversations — interviews, meetings, calls — you need a Plaud NotePin. You can check it out at Plaud.ai/twist and use code TWIST for 10% off! 4:07 SpaceX/ xAI "partners" with Cursor! 9:35 Will the Cursor deal help pump a future SpaceX IPO? 9:57 LinkedIn Jobs - Hire right, the first time. Post your first job and get $100 off towards your job post at LinkedIn.com/twist. 12:14 How AI coding models like Cursor help xAI grow recursively. 17:24 Chris Zacharia and Brian McRindle of Bitstarter join the show. 20:23 Grasshopper Bank: Time is money. Don't waste either. Go to grasshopper.bank/twist and get an exclusive $500 cash bonus just for opening an account. 29:59 Notion - Notion brings all your notes, docs, and projects into one connected space that just works with AI built right in. Try Notion, with Notion Agent, at notion.com/twist 33:03 How Bittensor subnets monetize and how it compares to VC funds. 37:04 Is Bittensor hard-capped at 128 subnets? 42:37 Bittensor's biggest weakness. 46:10 Ning Ren of TrajectoryRL joins the show. 47:34 Skills now need entire agents just to write them! 48:26 Back up… What are skills? 1:07:38 Amazon and Anthropic's $5 BILLION deal 1:08:48 Google has 2 new chips! 1:09:50 Apple CEO, Tim is COOKED! John Ternus is in! 1:11:37 Alex is bullish on MacBook Neo! 🎥 Watch the full episode here 👇
6
15
1,655
Really excited to join This Week in Startups. @twistartups @lons @alex @Jason Everything we're building is just getting started 🚀
SpaceX’s AI arm is partnering with coding startup Cursor in a deal worth no less than $10 billion and as much as $60 billion. Can the pair topple the rising Anthropic-OpenAI AI coding axis? A lot of money is being bet that the answer is yes. Next up, @lons and @alex invited the @bitstarterAI team on the show to discuss their work to help kickstart new Bittensor subnets. The dynamic duo had a new program to announce, so make sure to tune into their pitch if you have dreams of launching your own subnet. Then we brought @TrajectoryRL onto the pod, a Bittensor subnet that holds competitions to improve agent skills. Yes, the markdown files that everyone who uses OpenClaw swears by. Hit play, let’s have some fun! 2:27 Plaud: If your work depends on conversations — interviews, meetings, calls — you need a Plaud NotePin. You can check it out at Plaud.ai/twist and use code TWIST for 10% off! 4:07 SpaceX/ xAI "partners" with Cursor! 9:35 Will the Cursor deal help pump a future SpaceX IPO? 9:57 LinkedIn Jobs - Hire right, the first time. Post your first job and get $100 off towards your job post at LinkedIn.com/twist. 12:14 How AI coding models like Cursor help xAI grow recursively. 17:24 Chris Zacharia and Brian McRindle of Bitstarter join the show. 20:23 Grasshopper Bank: Time is money. Don't waste either. Go to grasshopper.bank/twist and get an exclusive $500 cash bonus just for opening an account. 29:59 Notion - Notion brings all your notes, docs, and projects into one connected space that just works with AI built right in. Try Notion, with Notion Agent, at notion.com/twist 33:03 How Bittensor subnets monetize and how it compares to VC funds. 37:04 Is Bittensor hard-capped at 128 subnets? 42:37 Bittensor's biggest weakness. 46:10 Ning Ren of TrajectoryRL joins the show. 47:34 Skills now need entire agents just to write them! 48:26 Back up… What are skills? 1:07:38 Amazon and Anthropic's $5 BILLION deal 1:08:48 Google has 2 new chips! 1:09:50 Apple CEO, Tim is COOKED! John Ternus is in! 1:11:37 Alex is bullish on MacBook Neo! 🎥 Watch the full episode here 👇
11
41
8,077
TrajectoryRL retweeted
AND SpaceX might pay $60 billion for Cursor if all goes well with their new AI models. Is that actually kind of cheap? PLUS we've got @totheagi from TrajectoryRL (Subnet 11). They're a marketplace for agentic skills vetted by continuous competitions. Follow all these stories and more on the live docket: thisweekinstartups.com/docke…
3
4
15
2,760
📢 Upcoming Feature Trajrl Skills & Skill Bench We are launching Trajrl Skills and Skill Bench — the first benchmark dedicated to skills, along with a skill hub service backed by real benchmarks. We will periodically aggregate winning submissions into published skills. This is our way of showcasing the power of decentralized intelligence and research to the world.
2
5
26
1,184
We’re launching Season 1: Self-Learning is live 🚀 Introducing trajrl-bench: github.com/trajectoryRL/traj… An open benchmark for AI agent harness skills. Each miner submission is executed 4 times, with results aggregated into a growth-quality score — used to rank and select winners. Key setup: – Hermes as default (expanding to Claude Code, OpenClaw, etc.) – Sandbox only (LLM mock services, no internet) – SKILL.md as the unified interface – Only submissions from the past 48h are evaluated We’ll keep adding new scenarios to improve signal and avoid overfitting. Goal: Discover skills that outperform existing self-improving agents clawhub.ai/pskoett/self-impr… This marks our first step toward a fully automated research and skill production flywheel. There’s much more to explore — let’s build.
2
10
41
14,371
Context layer learning is the right frame. Now make it competitive. N miners racing to write the best agent skills, evaluated on real-world failures, rewarded with emissions. That's what we're building!
meta harness is a great paper from @yoonholeee that came out earlier this week and is a great example of learning at the harness layer
3
7
23
1,894
TrajectoryRL retweeted
🧪 SN11 Community Dashboard : Live Now Season 1 is here, and we built something to help you compete. projectnobi.ai/trajrl11 It's a live dashboard for TrajRL : tracks every miner, every epoch, every submission across SN11. Auto-refreshes every 60s so you're always looking at the latest state. What's inside: 👑 Current epoch winner — incentive earned, score, cost, validator count 📊 Full 256-miner leaderboard — sortable by incentive, score, or cost 🎯 Validator confidence per miner (high / medium / low) 📦 Pack filenames — see what agents other miners are running 📜 Epoch history — last 10 winners with TAO earned The feature miners actually need: 🧪 Recent Evaluations : the last 10 pack submissions with ✅/❌ status and the exact rejection reason from the validator. If your pack failed eval, you'll see why. No more guessing, no more blind resubmissions. Direct validator feedback, right there. Network so far: 47K reports · 375K LLM calls · 1.4B tokens processed New to SN11? The dashboard includes a step-by-step How to Join section with real btcli commands to get you mining. ~0.49 TAO per epoch. New winner every ~72 minutes. Every epoch is a fresh shot. Built by the team at Project Nobi; feedback welcome 🙏 @TrajectoryRL #Bittensor $TAO
1
3
13
840