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
------------------------------
Original Message:
Sent: 31-03-2025 17:27
From: Kara K.W. Byun
Subject: Guide to an AI-Powered Workplace
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
Original Message:
Sent: 06-03-2025 09:28
From: Aya Pariy
Subject: Guide to an AI-Powered Workplace
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
------------------------------