Sign In

Tomas Vykruta

Founder & President @ EvolutionIQ. Twitter @tvykruta. Helping Injured & Disabled Individuals Return to Work Sooner. Google AI.

Tomas Vykruta is the Co-founder and President of EvolutionIQ, an AI-powered claims guidance platform for insurance companies.14 He has a background in technology and artificial intelligence, having spent nearly a decade working on machine learning and AI projects at Google before co-founding EvolutionIQ in 2019.25

Vykruta's expertise lies in data science and AI applications. He played a crucial role in developing EvolutionIQ's AI-driven claims guidance system, which helps insurers handle claims more effectively and accurately.1 The company's technology has been adopted by 70% of the top 15 U.S. disability carriers and is expanding into workers' compensation markets.1

In addition to his professional achievements, Vykruta has diverse interests and skills:

  1. He is a licensed commercial aircraft pilot and flight instructor.6
  2. He holds certifications in scuba diving and freediving.6
  3. He is multilingual, with proficiency in English, Czech, and working knowledge of Spanish, German, and French.6

Under Vykruta's leadership, EvolutionIQ has grown significantly, raising over $40 million in funding and achieving a valuation of over $200 million.12 Recently, in December 2024, EvolutionIQ was acquired by CCC Intelligent Solutions for $730 million, marking a significant milestone for the company.34

Highlights

Jul 31 · linkedin

Recursive Introspection: Teaching Language Model Agents How to Self-Improve is a new research paper on self-refining LLM's, incorporating error reasoning directly into Fine Tuning data for LLM's.

Here's a simplified breakdown of the RISE algo to achieve multi-turn correction:

  1. Initial Data Collection:

    • Collect a set of prompts and their corresponding desired outputs.
    • Example: For a prompt "Translate 'hello' to French", the desired output is "bonjour".
  2. Initial Model Training:

    • Train the model on the initial dataset using standard supervised learning.
    • The model learns to map prompts to outputs based on the provided examples.
  3. Generate Responses:

    • Use the trained model to generate responses for each prompt.
    • Example: The model translates "Translate 'hello' to French" as "salut".
  4. Identify Mistakes:

    • Compare the generated responses to the desired outputs to identify mistakes.
    • Example: "salut" is identified as incorrect since "bonjour" is the desired output.
  5. Create Correction Prompts:

    • For each incorrect response, create a new prompt asking the model to correct itself.
    • Example: "The translation 'salut' is incorrect. Try again to translate 'hello' to French."
  6. Generate Corrections:

    • The model generates a new response based on the correction prompt.
    • Example: The model might now generate "bonjour".
  7. Feedback Loop:

    • Continue this process iteratively, where each incorrect response leads to a new correction prompt.
    • This creates a multi-turn dialogue, enabling the model to refine its responses over multiple attempts.
  8. Fine-Tuning:

    • Fine-tune the model using the collected correction prompts and their correct responses.
    • The model learns to improve its initial responses based on the corrections provided.
  9. Evaluation:

    • Evaluate the model's performance on a separate validation set to ensure it can generalize the corrections.
  10. Deployment:

    • Deploy the improved model for real-world use, where it can continue to refine its responses based on user feedback.

This iterative fine-tuning process helps the model learn from its mistakes and improve its performance over multiple turns.

(thanks Andy C for sharing this) https://lnkd.in/gGtvrxPA

Jun 20 · linkedin

BREAKING -> Claude 3.5 Sonnet, Anthropic's latest model was just released, and it's significantly better than Google's Gemini 1.5 Pro Model.

By these benchmarks it's now outperforming OpenAI's GPT-4o in all but 2 categories.

spoiler: It's a poor math student.

It's significantly better than GPT4o at: -reasoning over text -code -graduate level reasoning

https://lnkd.in/ePZB8BNp

BREAKING -> Claude 3.5 Sonnet, Anthropic's latest model was just released, and it's significantly be

Related Questions

What inspired Tomas Vykruta to start EvolutionIQ?
How did Tomas Vykruta's experience at Google influence his work at EvolutionIQ?
What are the main challenges Tomas Vykruta has faced in developing EvolutionIQ's AI platform?
How does EvolutionIQ's claims guidance system improve the insurance claims process?
What are some success stories from clients who have used EvolutionIQ's services?
Tomas Vykruta
Tomas Vykruta, photo 1
Tomas Vykruta, photo 2
Add to my network

Location

New York, New York, United States