An AI-powered Knowledge Discovery Platform
Joined April 2022
- Tweets101
- Following12
- Followers3.7K
- Likes27
At @aiDotEngineer NYC, Samaya's @AshwinParan built on our earnings prediction research, exploring how AI models reason through predictions and how we might combine the best aspects of human and AI reasoning in the future.
Watch below ↓
Samaya AI retweeted
📺 Spotted on @theinformation TV: @samaya_AI founder & CEO @maithra_raghu was featured to discuss her company’s AI agents for finance that aim to transform global financial market information into investment conviction
👉🏽 Check it out at the 28:55 mark. theinformation.com/titv
To train better earnings forecasters, we need events whose outcomes the model hasn’t already learned. But how far back can we reliably evaluate AI earnings predictions without prior knowledge affecting the results?
When prompted directly, Nemotron Ultra recalled exact EPS for just 2 of 272 historical events. Yet its answer probabilities showed a different pattern: the oldest earnings answers received ~75x the probability of the most recent ones.
Recall can miss prior-knowledge signals. Measuring them could help us choose more usable post-training data.
Read the research ↓
We gave AI agents the same earnings prediction task as expert analysts.
Using Samaya’s finance-specific prediction harness, the latest frontier models (Fable 5.1, Opus 5.5, GPT-6 Astra) outperformed a harder, bias-corrected consensus baseline.
The models gathered new evidence, calculated the financial impact of events, and adjusted their predictions away from consensus.
This is a critical inflection point for AI in finance.
Full research ↓
AI research agents often fail on the details, not the reasoning.
We trained an advisor model using Hindsight Structured Advice Distillation (HSAD) to learn from our research agent’s past failures and guide it with a question-specific plan.
The result: better research quality without spending more compute.
On FrontierFinance, our public benchmark:
🔹 56.6% quality, #1 on the leaderboard
🔹 Beats our previous best at 37% lower cost
🔹 Outperforms the best frontier model (Claude Fable 5.1, 55.9%)
More on how it works ↓
Fifty new workflows are live in Samaya.
A hard-to-get management meeting just landed on your calendar. The last thing you want is to waste that time asking a question they've already answered.
Run a Meeting Prep workflow to catch up on the key debates, current events, what management said at the last conference, and the questions you need answered, so you can walk into the room prepared.
Buy-side and sell-side. Built by analysts who used to do it by hand.
Samaya AI retweeted
We partnered with @AnthropicAI to evaluate @claudeai Fable 5.1 pre-launch on FrontierFinance! Fable 5.1 becomes the best performing frontier model by a wide margin, scoring 55.9% compared to 49.2% for Fable 5 (the prior best performing frontier model.)
This gain largely comes from Fable 5.1 carrying out more and better tool calls, e.g. calling and anchoring better on authoritative sources.
The increased tool calls does come with increased cost though -- we observe Fable 5.1 is about 1.7x as expensive as Fable 5.
Exciting results and lots more work ahead to continue advancing agentic capabilities!
A month ago we released FrontierFinance, an open benchmark for the frontier capabilities of finance AI agents. The response from community has been terrific, and the latest models are already making fast progress.
Today we're publishing the technical report: our annotation process, a deep analysis of the dataset, and a close look at how current systems and models actually behave, with insights we hope will shape the next generation of frontier models and harnesses.
Full report 👇
Imagine an alert that understands that a document has referenced something you care about. Set up a content-based alert in Samaya and receive the read across that you would have otherwise missed, now delivered directly to your inbox.
Try: “Monitor expert transcripts for mentions of ad tech that impact companies like Meta and Google.”
Create your first content-based alert in Samaya today.
Bond data, live in @samaya_AI via Finnhub.
Historical and last price, maturity, coupon, and bond details across US corporate issuers. One tool for the whole capital structure.
Available to all Samaya accounts today.
