Technology and Innovation Community

 View Only
  • 1.  Guide to an AI-Powered Workplace

    Posted 06-03-2025 09:28
      |   view attached

    Good morning Community!

    From Vision to Reality: how AI changes our workplaces? A survey was done with the Stepstone Group and Totaljobs

    1. Current State of AI Integration

    • A study involving over 5,000 participants from Germany and the UK reveals that while 44% of UK workers anticipate AI revolutionizing their tasks within the next five years, only 21% currently feel very comfortable using it

    2. Employee Confidence and Experience with AI

    Despite AI's potential, half of UK workers have never used it, and over a third (39%) lack a clear understanding of its application in their industry.

    3. Recommendations for Effective AI Integration

    • Showcase AI-Readiness in Talent Attraction: Position your company as forward-thinking by highlighting AI initiatives to attract top talent.

    • Communicate and Explain AI Benefits: Clearly articulate how AI can enhance productivity and job satisfaction to alleviate employee concerns.

    • Involve Employees in AI Implementation: Engage staff in the AI adoption process to foster a sense of ownership and reduce resistance.

    • Invest in AI Training and Development: Provide comprehensive training programs to equip employees with necessary AI skills

    4. Employee Expectations and Talent Attraction

    • Nearly half (46%) of UK workers expect employers to invest more in AI to boost productivity. Additionally, 38% view companies recognized as AI leaders as more attractive employers.

    How do you feel about this and how AI impacts your day-to-day work and that of your team?



    ------------------------------
    Aya Pariy
    ------------------------------


  • 2.  RE: Guide to an AI-Powered Workplace

    Posted 06-03-2025 11:04

    Great update Aya.

    Adding to this below is a snapshot from Statista on the usage of generative AI at work or outside of work (2023).

    Almost a quarter of the respondents working in FS are regularly using AI tools thus lagging only respondents from the TMT industry.

    Usage og generative AI tools
    Best,
    Todor


    ------------------------------
    Todor Kostov
    Director
    ------------------------------



  • 3.  RE: Guide to an AI-Powered Workplace

    Posted 07-03-2025 22:18

    Great article. Interesting to see finance professionals with 50% no experience. 

    In finance, we continue to see challenges with dealing with sensitive data unlike in other industries where data is easier to flow across jurisdictions. A lot of the servers which run the AI backend are in the US. This means that for people based outside of the country, any query relating to a sensitive data point can be a breach of regulations. Any document or information which alludes to an M&A deal in Europe or information on a Swiss banking client being processed by a server in US could have severe repercussions. 

    Unfortunately, the risk and onus if often on the front office to avoid making such mistakes and diligently review or retract / mask sensitive information in large documents which sometimes takes longer than doing a manual task yourself and not utilising the AI technology. These risks continue to be a challenge and headwind to wider adoption but no doubt solutions for these issues will continue to be worked on and rolled out. 



    ------------------------------
    Shane Jocelyn
    Investment Analyst
    ------------------------------



  • 4.  RE: Guide to an AI-Powered Workplace

    Posted 31-03-2025 17:27

    One of the biggest blockers to adoption of LLMs in enterprise workplace settings has been explainability, especially in heavily regulated industries like financial services. The work that Anthropic is doing to head-on address explainability, by observing LLMs in action, is fascinating. Check it out: 

    On the Biology of a Large Language Model

    Circuit Tracing: Revealing Computational Graphs in Language Models

    tl;dr from MIT Technology Review:

    "The AI firm Anthropic has developed a way to peer inside a large language model and watch what it does as it comes up with a response, revealing key new insights into how the technology works. The takeaway: LLMs are even stranger than we thought.

    ... Shedding some light on how these models work exposes their weaknesses, revealing why they make stuff up and why they can be tricked into going off the rails. It helps resolve deep disputes about exactly what these models can and can't do. And it shows how trustworthy (or not) they really are.

    Batson and his colleagues describe their new work in two reports published today. The first presents Anthropic's use of a technique called circuit tracing, which lets researchers track the decision-making processes inside a large language model step by step. Anthropic used circuit tracing to watch its LLM Claude 3.5 Haiku carry out various tasks. The second (titled "On the Biology of a Large Language Model") details what the team discovered when it looked at 10 tasks in particular."



    ------------------------------
    Kara K.W. Byun
    Head of Fintech
    ------------------------------



  • 5.  RE: Guide to an AI-Powered Workplace

    Posted 04-04-2025 15:53
    Edited by Todor Kostov 05-04-2025 10:30

    Great updates and info Kara.

    Furthermore, here is a recent study from the Alignment Science Team @ Anthropic that shows that AI models quite often conceal their true reasoning processes when explaining answers to a user.

    Of big concern here is user's ability to monitor and understand AI decision-making.

    Brief details about the study:

    • It evaluates Claude 3.7 Sonnet and DeepSeek R1 on their chain-of-thought faithfulness, gauging how honestly they explain reasoning steps
    • Models were provided hints like user suggestions, metadata, or visual patterns, with the CoT checked for admission of using them when explaining answers
    • Reasoning models performed better than earlier versions, but still hid their actual reasoning up to 80% of the time in testing
    • The study shows models were less faithful in explaining their reasoning on more difficult questions than simpler one

    In conclusion, all this brings furher complications rather than clarity about what sits behind the actual reasoning for models, especially for complex behaviour and problems.

    Todor



    ------------------------------
    Todor Kostov
    Director
    ------------------------------