Reply to: Demand for AI "Surging"

[willendure]

Maybe 2? Seems like a low enough number to not be unsure about.

Ok it was 3. And one of them I worked for twice. And one of them I only worked for for 3 months and it was fully remote, so less of an opinion on that one. The other 2 were great though.

[Snooky]

I have worked for maybe 2 US multi-nationals

Maybe 2? Seems like a low enough number to not be unsure about.

[edison]

Fine by me, would love to work for an American corporation. I have worked for maybe 2 US multi-nationals and had great experiences both times. Americans are funny, but they do bring a certain energy to the workplace.

Sounds better than their weird "Zones" idea - why tie AI to a geographical location? There is some kind of outmoded thinking there, but I guess the real aim of this is to try and channel some money into certain parts of the UK where there is "brain power".

Most of the brain power and associated funding is roughly in the Oxford/Cambridge/London triangle. The vast majority of VC funding for startups is in this area. Until that changes, it's difficult to see the government really being able to shift some of that to the likes of Manchester or Leeds or Scotland for example.

[SussexSeagull]

Erm...

Back on, apparently.

https://www.bbc.co.uk/news/articles/crr05jykzkxo

[willendure]

Erm...

What will he do when he finds that all the serious UK-based AI expertise is now working for America.

Fine by me, would love to work for an American corporation. I have worked for maybe 2 US multi-nationals and had great experiences both times. Americans are funny, but they do bring a certain energy to the workplace.

Sounds better than their weird "Zones" idea - why tie AI to a geographical location? There is some kind of outmoded thinking there, but I guess the real aim of this is to try and channel some money into certain parts of the UK where there is "brain power".

[malvolio]

The government are right to make a plan and try and manage the situation and get the best out of it because it is going to happen anyway.

Erm...

What will he do when he finds that all the serious UK-based AI expertise is now working for America.

[SussexSeagull]

The government are right to make a plan and try and manage the situation and get the best out of it because it is going to happen anyway.

[willendure]

And so on, I am sure you can easily reproduce and have your own dig into it with ChatGPT.

Looks positive to me, but other than the specific mention of Culham, a bit thin on details at the moment.

[willendure]

What specific mechanisms are discussed for helping startups and SMEs?
ChatGPT said:

ChatGPT

The AI Opportunities Action Plan Government Response outlines several mechanisms aimed at helping startups and small-to-medium enterprises (SMEs) benefit from AI advancements and adoption. These mechanisms include:
1. AI Growth Zones (AIGZs)

• The creation of AI Growth Zones is a key initiative to support AI infrastructure and encourage investment in AI development. These zones will offer enhanced access to essential resources like power and planning approvals to accelerate AI infrastructure build-outs.
• Private-sector partnerships are emphasized, which could help SMEs and startups access world-class AI data centers, computing resources, and strategic support.
• The first AI Growth Zone will be established at Culham, with plans for more zones to be identified by Spring 2025. These zones could foster an environment where AI-driven startups can thrive.

2. Access to Data

• The establishment of the National Data Library aims to unlock public sector data and make it accessible to AI researchers, startups, and innovators, providing them with valuable datasets to fuel their AI projects.
• In addition, the government plans to strategically shape data collection to better meet the needs of AI developers, ensuring relevant, high-quality datasets are available for AI innovation.

3. AI Talent Support

• Programs to attract, train, and retain AI talent are critical for startups and SMEs. The government is working to develop programs to train the next generation of AI scientists and entrepreneurs, ensuring that small businesses have access to skilled workers.
• AI fellowships and scholarships will also support the development of a talented workforce, which startups and SMEs can tap into for innovation and growth.

4. Public Procurement Support

• Startups and SMEs will benefit from a reformed AI procurement process that aims to be more accessible. The “Scan, Pilot, Scale” approach involves helping startups pilot AI projects within government services and scale them up once proven successful.
• The procurement process will be designed to reduce barriers to entry, allowing smaller companies to compete for public sector contracts and gain exposure to larger markets.

5. Funding and Investment

• Government initiatives, including the support for AI Growth Zones, will help attract private-sector investment into UK-based AI companies, benefiting startups and SMEs.
• A focus on smart procurement and the development of mission-driven AI tenders will direct funding toward innovative projects led by smaller companies.

6. AI Champions and Sector-Specific Support

• The government will appoint AI Champions within specific sectors (e.g., healthcare, financial services) to help identify adoption opportunities. These champions will also guide startups and SMEs in how they can best engage with government initiatives and industry trends to scale their solutions.

7. Pilot Programs and Testing Grounds

• The AI Research Resource will be expanded to provide access to powerful AI supercomputers, offering startups and SMEs the ability to test and develop AI applications without the heavy upfront investment in infrastructure.
• Through public-private partnerships and pilot programs, the government will provide a platform for smaller businesses to prove the value of their AI solutions and scale them.

Conclusion


The UK government is creating a supportive ecosystem for AI startups and SMEs by providing access to resources, talent, data, funding, and opportunities for collaboration with both the public and private sectors. These initiatives are aimed at lowering barriers to entry, fostering innovation, and creating pathways for growth within the AI sector.

[willendure]

Does it indiciate how much will be invested to adopt AI in public services?
ChatGPT said:

ChatGPT

The AI Opportunities Action Plan Government Response does not specify a concrete total investment amount solely for adopting AI in public services. However, it highlights a commitment to the "Scan, Pilot, Scale" approach, which involves:

1. Piloting AI projects in public services to assess their feasibility and benefits.
2. Scaling successful pilots with senior support and central funding.
3. Developing frameworks and infrastructure for AI adoption, including streamlined data access and procurement processes.

While the document emphasizes funding strategies and support mechanisms (e.g., central funding for scaling successful pilots), the exact financial allocation for these initiatives appears to be part of broader commitments tied to infrastructure, talent, and regulatory development rather than a distinct, defined figure. Additional details might emerge in the planned Spending Review in Spring 2025.

[willendure]

Does it say where AI growth zones will be located?
ChatGPT said:

ChatGPT

Yes, the AI Opportunities Action Plan Government Response mentions that the first AI Growth Zone (AIGZ) will be located at Culham, the headquarters of the UK Atomic Energy Authority (UKAEA). This is subject to the agreement of a public-private partnership that delivers local and national benefits. The government also plans to identify and select additional AI Growth Zones by Spring 2025, taking into account factors such as regional growth opportunities, energy requirements, and alignment with local and national strategies.

[willendure]

So I downloaded the AI Action Plan PDF from gov.uk: https://www.gov.uk/government/public...nment-response

And to be true to the cause, I asked an AI to give me a summary of the plan. Here it is:

The AI Opportunities Action Plan Government Response outlines the UK's strategy to harness the potential of artificial intelligence (AI) to enhance economic growth, improve public services, and secure a leading global position in AI. Here’s a summary of the key points:
Foundations for AI

1. AI Infrastructure: A plan to expand AI computing capacity by 20x by 2030, including the establishment of a supercomputing facility and AI Growth Zones to attract private sector investment and build robust AI data centers.
2. Energy Needs: Creation of an AI Energy Council to address the energy demands of AI with renewable solutions.
3. National Data Library: Development of a secure repository for public sector data to facilitate AI research and innovation.

Skills and Regulation

1. AI Talent Development: Expansion of scholarships and training programs to address AI skills gaps and enhance diversity in the talent pool.
2. Regulation: Establishment of frameworks to promote safe, ethical AI development and use, balancing innovation and safety.

AI for Public Services and Economic Growth

1. Adoption in Public Services: Implementation of AI in public services using a “Scan, Pilot, Scale” methodology, with AI Champions appointed to facilitate adoption.
2. Homegrown AI: Measures to strengthen UK-based AI companies, attract global talent, and support startups to maintain the UK’s competitive edge.

Collaborative Efforts

1. Private-Public Collaboration: Initiatives to promote AI adoption across sectors, including partnerships, procurement strategies, and sharing of best practices.
2. Global Partnerships: Building international collaborations to enhance compute capabilities and share AI advancements.

Next Steps


The government will continue refining its AI strategy, monitor progress through the AI Opportunities Unit, and integrate these initiatives into broader industrial strategies by 2025.

This comprehensive plan underscores the UK’s ambition to become a global AI leader while ensuring ethical, inclusive, and sustainable development.

[willendure]

Action plan, no less: https://www.bbc.co.uk/news/articles/crr05jykzkxo

[dsc]

True but...

Part of the reason LLMs have been possible, is because of unsupervised learning. There is masses of text available to train on, and the training is just a game of guess-the-next-word. Masses of data, masses of compute, and humans just wrote the code for the training, not actually human in the loop to conduct the training.

Datasets for the instruction following training did have to be prepared by hand.

o1 was trained using some kind of reinforcement learning - the Q* or Q learning thing that was hyped a while back. Reinforcement learning is also fully automatic, no human in the loop to conduct the training. This is how AIs learn to play video games for example. They just play and play with the aim of staying alive for longer, or getting a higher score or whatever metric their performance can be measured against.

There's still a human in the loop, the text, whatever you feed it, was made by humans. It's not created out of thin air, someone put effort / work into all that data that's available for training. I know the process is unsupervised, but it's not like AI can just make it's own training data blocks and train itself, you have to feed it stuff made by someone. Same principle with testing, you define a "win" scenario by declaring acceptable results and those are human defined.

[willendure]

Well you always have to train AI, some humans have to get involved at some stage.

True but...

Part of the reason LLMs have been possible, is because of unsupervised learning. There is masses of text available to train on, and the training is just a game of guess-the-next-word. Masses of data, masses of compute, and humans just wrote the code for the training, not actually human in the loop to conduct the training.

Datasets for the instruction following training did have to be prepared by hand.

o1 was trained using some kind of reinforcement learning - the Q* or Q learning thing that was hyped a while back. Reinforcement learning is also fully automatic, no human in the loop to conduct the training. This is how AIs learn to play video games for example. They just play and play with the aim of staying alive for longer, or getting a higher score or whatever metric their performance can be measured against.