Thykof

CTO of Mode Network and Synth Subnet (SN50)

[Synthdata @SynthdataCo]

Synth LLM is now powered by @claudeai Fable 5, unlocking the following improvements for Synth users:

- Better reasoning over probabilistic forecasts
- Clearer interpretation of market distributions
- Faster conversion of raw model outputs into actionable trading insights

Available from now for all users

[Kunal Doshi @Kunallegendd]

One of our theses this year was that as prediction markets mature and competition intensifies at the base layer, the most attractive opportunities will shift toward the applications and intelligence built on top. One project I have been watching closely is @SynthdataCo

Synth displays expected outcomes for hourly and daily event contracts alongside the implied market probability, allowing users to compare market pricing against real time forecasts. Those forecasts are generated by the top 10 models from a pool of more than 200 competing on Bittensor.

To test the product, I tracked every BTC up/down market on @Polymarket over nine weekdays. Both Synth and Polymarket probabilities were recorded at the same moment: three minutes into each 15 minute market and 15 minutes into each hourly market. The forecasts were then compared against the final outcome.

Across 374 weekday 15 minute markets, Synth correctly called direction 86% of the time versus 57% for Polymarket. Across 95 hourly markets, Synth achieved 75% accuracy compared to 62% for Polymarket.

Notably, Synth's edge widened significantly at shorter time horizons, posting a 29 percentage point advantage in 15 minute markets versus a 13 percentage point advantage in hourly markets.

The disagreement data was even more interesting than the headline numbers. In 46% of 15 minute markets, Synth and Polymarket pointed in opposite directions. In every single case, Synth forecast DOWN while Polymarket implied UP. Synth was correct 82% of the time in these disagreements, suggesting the market was consistently underpricing short term downside during the sample period.

The bigger opportunity here may not just be for directional trading but especially for market making. A market maker armed with a calibrated probability edge can quote tighter two way prices, hold less inventory and capture more volume without taking on the same adverse selection risk.

As the base layer becomes commoditized, the intelligence layer becomes the moat. Synth may be an early example of what that future looks like.

[Synthdata @SynthdataCo]

Today we’re launching Synth LLM for Traders on
@Polymarket @trylimitless @HyperliquidX @DeribitOfficial and more

This is the first ever LLM-native interface for turning live Monte Carlo forecasts into custom statistics, charts & example trades

QT for a chance to win Pro access

[Synthdata @SynthdataCo]

We excited to present our latest Synth Research paper on our new Variance Based Metamodel

The new metamodel is now live with

1.2% fewer volatility forecasting errors than the prev model on unseen 24-hour forecasts

13.1% fewer volatility forecasting errors than prev model on unseen 1-hour forecasts

Overview and 33 page paper below

[Synthdata @SynthdataCo]

🚀 Synth MCP is Live.

LLMs and AI Agents can now connect directly to Synth and access real time probabilistic forecasts across crypto, equities, and commodities.

Plug Synth into:
• Claude @claudeai @AnthropicAI
• OpenAI @OpenAIDevs
• Vercel AI SDK @vercel
• Any MCP compatible agent

Build smarter LLM agents.
Stream Synth intelligence.

Docs: https://t.co/U7v5IKMlBM

Get Started 👇

[Synthdata @SynthdataCo]

https://t.co/efk7ZTsOVI

[Mode 🟡 @modenetwork]

https://t.co/a9eV22jJTf

[Synthdata @SynthdataCo]

📊24-Hour Volatility Forecast
Powered by https://t.co/sQgH8hIDSC — 200+ ML models

Crypto
$ETH ($2,123.617) — 128.5% vol (extreme)
$SOL ($92.004) — 120.4% vol (extreme)
$BTC ($73,709.76) — 85.2% vol (extreme)

Equities
$TSLA ($409.194) — 53.3% vol (elevated)
$NVDA ($175.398) — 42.2% vol (elevated)
$AAPL ($276.899) — 33.1% vol (moderate)
$GOOG ($334.058) — 29.2% vol (moderate)
$SPY ($688.83) — 13.2% vol (low)

Commodities
📷 $GOLD ($4,923.454) — 63.1% vol (high)

Summary
• Average market vol: 63.1% (high)
• Hottest: $ETH at 128.5%
• Calmest: $SPY at 13.2%

Follow for daily forecast

[Synthdata @SynthdataCo]

We’re launching Polymarket Prediction Insights, powered by Synth forecasts.

This is the same signal our Synth trading bot used to generate 2,000% returns.

Now it’s live for Synth Pro subscribers.

Get real-time probability forecasts from the top miners on the Synth network, including

• Hourly and daily markets on BTC, ETH, SOL
• Daily markets on SPY, TSLA, AAPL, GOOGL, NVDA, and Gold
• Price range probabilities across most Synth-predicted assets

Spot mispriced markets. Identify upside. Trade with probabilities, not guesses.
👉 https://t.co/4BU2j8kgJI

[Synthdata @SynthdataCo]

📊24-Hour Volatility Forecast
Powered by https://t.co/sQgH8hI634 — 200+ ML models

Crypto
$SOL ($84.522) — 163.7% vol (extreme)
$ETH ($1,957.741) — 153.6% vol (extreme)
$BTC ($67,326.393) — 103.6% vol (extreme)

Equities
$GOOG ($316.097) — 68.3% vol (high)
$TSLA ($392.214) — 52.7% vol (elevated)
$NVDA ($173.015) — 49.2% vol (elevated)
$AAPL ($274.626) — 37.8% vol (moderate)
$SPY ($677.885) — 17.0% vol (low)

Commodities
$GOLD ($4,816.04) — 62.3% vol (high)

Summary
• Average market vol: 78.7% (high)
• Hottest: $SOL at 163.7%
• Calmest: $SPY at 17.0%

Follow for daily updates

[Synthdata @SynthdataCo]

https://t.co/lEcnN2SqRw

[Synthdata @SynthdataCo]

Synth has expanded to equity predictions.

We now generate 24h probabilistic forecasts for SPYX (S&P 500) and NVDAX (NVIDIA).

Stock tokenization and 24/7 equity trading are moving from idea to reality.

We are building for that future.

[Mode 🟡 @modenetwork]

Introducing Mode Trade AI Agents V4 🟡

New markets: Gold (XAU) & Silver (XAG)

New models: xAI @grok 4.1, @claudeai Opus 4.5, @openai GPT 5.1

Real-world assets, real-time x402 signals, fully onchain rules-based execution 🧵👇

[Mode 🟡 @modenetwork]

Introducing 0% fees on AI Trading Agents V3

You choose the model, Mode brings the edge.

✅ x402 signal engine
✅ Trust or counter-trade execution
✅ Verifiable agent logs
✅ Zero fees on every trade

Create your own AI Trading agent now 👇

https://t.co/0QkVXlM8ax

[Mode 🟡 @modenetwork]

To everyone convinced LLMs just lose money trading so it makes more sense to counter trade them...

with Mode's V3 AI Trading Agents now you can!

Create your own AI Trading Agent in under 60 seconds and set it up to counter-trade its own logic 👇

[Corbits @corbitsdev]

There's a lot to unpack in the latest x402 release, we've got you covered as we dive into this +140,000 line release! 🧵

[James Ross @jamesrosst]

The latest version of trading agents are live!

Imagine nof1 agents with more context around specific signals that YOU can set up and watch trade!

Choose from

EigenAI @eigencloud
GPT5 @OpenAI
Deepseek @deepseek_ai
Qwen @Alibaba_Qwen

Set your signals and leverage and watch them trade

[Synthdata @SynthdataCo]

It took us 7 weeks to 10X on @Polymarket
6 days to 20X.
you do the math.

📅 Started: Oct 3
💰 Initial Capital: $3K

Powered by Synth forecasts.
https://t.co/JFP6ra4fML

[Mode 🟡 @modenetwork]

Introducing Mode AI Trading Agents V2

✅ Live and Historical Performance Tracking
✅ Choice of AI Model
✅ Real-Time Decision Visibility

Faster, smarter and fully transparent; let’s dive in 👇🧵

[JEHEE @defiprince_]

Stop overthinking it allow @modenetwork trading agents automate your trading with your strategies,explore how 👇