Suggestions
Evangelos Pappas
Principal Data & Platform Engineer for Fintech, AdTech and Web3
Evangelos Pappas, a prominent Tech Entrepreneur and Technologist, has been leading the strategy and development of several successful tech initiatives. He has worked in different verticals including FinTech, Telecoms, supply chain, AdTech, and energy distribution. Mr. Pappas has proven experience in managing small to medium tech teams comprising three to seven members of organizations of various sizes. With his expertise in distributed computing, Blockchain networks, large scalable enterprise applications, and integrations, he holds the position of CEO and Co-Founder at Ocyan, a technology-driven company that specializes in enterprise infrastructure as a service.
Mr. Pappas graduated with a Bachelor's degree in Computer Science from the University of Wales, where he honed his programming skills. He also studied Entrepreneurship Development Program, Management, and Leadership at MIT Sloan School of Management. Prior to his current position, he worked as a Blockchain Engineer at Shell, Tech & Blockchain Advisor at TransferX Ltd, Software Architect Consultant, Tech & Blockchain Advisor at Evalonlabs, and a number of other organizations where he developed and deployed various technologies.
In general, Mr. Pappas has remarkable expertise in managing teams and has profound knowledge about scalable enterprise applications, distributed systems, and Blockchain technologies. He is a competent solution architect and software developer, skilled in JavaScript, Java, and Android programming. An avid learner, Mr. Pappas is interested in exploring new technologies such as Quantum Computing, Artificial Intelligence, and their possible applications.
Highlights
Great paper summarizing the prompt techniques - The Prompt Report.
- 58 text-only prompting techniques including zero-shot, few-shot, thought generation, ensembling, self-criticsm, and decomposition techniques. Few-shot CoT performs the best among the few techniques they benchmarked
- Prompt Engineering: Meta prompting, auto prompt, automatic prompt engineer, gradient free instructional prompt search, prompt optimization with textual gradients, RLPrompt, dialogue-comprised policy-gradient-based discrete prompt optimization
- Answer Engineering: Answer shape, answer space, answer extractor
- Agents: tool use agents, code-based agents, observation-based agents, RAG
- Security: prompt hacking (prompt injection, jailbreaking), risks (data privacy, code generation concerns, customer service), hardening measures ( prompt-based defense, guardrails, detectors).
- Alignment: ambiguity, biases, calibration, prompt sensitivity
🔗arxiv.org/abs/2406.06608
We need to decentralize AdTech, it's already being too late.
#adtech #hubspot #advertising #MarkTech #google
