NewsLiquid
AI Agent-driven automated financial decision and execution layer. Newsliquid transforms global news data directly into trading actions through AI agents, collapsing the gap between information and execution. As markets move faster and agents become first-class actors on-chain, automated decision rails become a core piece of trading infrastructure.
7D Momentum
Velocity of growth — engagement quality folded in at 35%
Ranked by a composite of views, reach per follower, likes and bookmarks — normalised against this account's own peak.
- #118d agostrong: views
Introducing newsliquid-3.0-pro Building on the System One decision paradigm behind TypeSafe’s Jev @typesafeai , a specialist model purpose-built for real-time market news triage and conditional impact assessment. https:…
502330k41 - #218d agotop: views
In LLM system design, "broad-reasoning Agent pipelines" and "ultra-fast System One decision primitives" are diverging into distinct architecture paths. For real-time market impact assessment, NewsLiquid-3.0-pro adapts T…
1011.1k0 - #318d agotop: views
From text classifiers and prompt engineering to dedicated System One decision interfaces, specialized small-footprint models are demonstrating clear efficiency advantages in targeted domain tasks. Full blog post and ben…
0025731 - #418d agotop: views
What is a Decision Model (System One)? Unstructured text outputs from general LLMs are difficult to parse directly into downstream code. TypeSafe introduced Jev and RLCD (Reinforcement Learning for Calibrated Decisions)…
0017800 - #518d agotop: views
From General Jev to Domain Specialization General-purpose decision models often struggle with complex financial counter-signals (e.g., beat on earnings but lowered guidance). NewsLiquid 3.0 Pro addresses this through spe…
0015990
Latest activity from @newsliquidX.
From text classifiers and prompt engineering to dedicated System One decision interfaces, specialized small-footprint models are demonstrating clear efficiency advantages in targeted domain tasks. Full blog post and benchmark details: https://t.co/AUruvVND8X
System Integration & Production Pipeline Model outputs map directly to downstream system logic: • Filter noise below 30 points • Trigger real-time alerts or execution hooks for high-impact directional signals • Enable multi-asset parallel scoring per incoming news item
Decoding Strategy: Short-sequence Autoregressive Instead of multi-token Chain-of-Thought (CoT) reasoning, the model uses short-sequence autoregressive decoding. It outputs only [Score] + [Direction] and immediately halts generation. By concentrating compute into a single joint
Benchmark Results (FinTech News Impact Benchmark v2) Evaluated across 200 standard financial news events: • NewsLiquid-3.0-pro: 91.41% accuracy, 186.8 ms avg latency, 191.0 ms P99 • Jev 1.13.0: 72.41% accuracy, 180.6 ms avg latency On Information Rate (combining accuracy
From General Jev to Domain Specialization General-purpose decision models often struggle with complex financial counter-signals (e.g., beat on earnings but lowered guidance). NewsLiquid 3.0 Pro addresses this through specialized domain optimization: Supervised training over
In LLM system design, "broad-reasoning Agent pipelines" and "ultra-fast System One decision primitives" are diverging into distinct architecture paths. For real-time market impact assessment, NewsLiquid-3.0-pro adapts TypeSafe’s Jev / System One decision paradigm specifically
What is a Decision Model (System One)? Unstructured text outputs from general LLMs are difficult to parse directly into downstream code. TypeSafe introduced Jev and RLCD (Reinforcement Learning for Calibrated Decisions) to formalize decision-making as typed API interfaces.
Introducing newsliquid-3.0-pro Building on the System One decision paradigm behind TypeSafe’s Jev @typesafeai , a specialist model purpose-built for real-time market news triage and conditional impact assessment. https://t.co/PKexHTh7cj
Only Newsliquid Can Do. GAMMA DATA IS NOW LIVE! https://t.co/qVb8mJvmL4 https://t.co/nlP0JC4SRE
NewsLiquid Agent AI is now live. Research starts right inside the trading interface. Ask where the move started. The Agent connects the fundamentals to your position and shows what the market is pricing in. Start with one question and get the context behind the trade. https://…