Browse Source

Update Post.md

pull/26358/head
Alper Ebiçoğlu 3 weeks ago
parent
commit
87f08e8df1
  1. 29
      docs/en/Community-Articles/2026-10-29-DevAI-Conference-Review/Post.md

29
docs/en/Community-Articles/2026-10-29-DevAI-Conference-Review/Post.md

@ -173,6 +173,13 @@ Their approach, called **NER-RAG**, combines traditional NLP with LLMs:
This reduces unnecessary LLM calls while making retrieval more predictable.
For example in a prescription the keword "Fentanyl" can be mentioned as many different alternatives like "Fentanylum", "Fentanylium", "Fentanil", "Sufentanil", "Remifentanyl".
Read more about NER:
- [graphrag.com/reference/preparation/ner/](https://graphrag.com/reference/preparation/ner/)
- [medium.com/@uaqureshi_61924/what-is-named-entity-recognition-ner-and-why-is-it-used-in-nlp-and-llm-based-ai-applications-c27184992b17](https://medium.com/@uaqureshi_61924/what-is-named-entity-recognition-ner-and-why-is-it-used-in-nlp-and-llm-based-ai-applications-c27184992b17) (*Turkish so translate to your language*)
![NER-RAG architecture with entity extraction and LLM validation](IMG_25688.png)
### 4. Significant Cost and Scalability Improvements
@ -186,9 +193,7 @@ The speaker presented some interesting performance figures from their approach:
![NER-RAG cost and scalability improvements](IMG_25693.png)
### Key Takeaway
**Not every AI problem needs to be solved entirely with LLMs.**
> **Not every AI problem needs to be solved entirely with LLMs.**
This session shows how combining traditional NLP, structured entity extraction, hybrid search and selective LLM validation can produce a more deterministic and cost-efficient retrieval system.
@ -202,7 +207,9 @@ The most interesting architectural decision was **moving expensive processing fr
**Speaker:** Borys Stokalski, Global Partnership on AI / OECD.AI
Borys Stokalski discussed the challenges and risks emerging from increasingly autonomous AI systems, particularly in software development. His central argument was that **the biggest challenges of AI adoption may come from how we use, manage and scale these systems rather than from the technology itself.**
Borys Stokalski is from OECD (Organisation for Economic Co-operation and Development)'s sub-department [OECD.AI](https://oecd.ai/en/) which discusses the challenges and risks emerging from increasingly autonomous AI systems, particularly in software development. By the way OECD.AI (OECD AI Policy Observatory), **started in February 2020 by OECD** in Paris and EU countries + USA + Japan + South Korea + Turkey are also members of this community.
His central argument was that **the biggest challenges of AI adoption may come from how we use, manage and scale these systems rather than from the technology itself.**
![We Have Met the Enemy and It Is Us](IMG_25712.png)
@ -218,7 +225,7 @@ As AI systems become more autonomous, three major challenges emerge:
### 2. AI Coding Productivity Doesn't Guarantee Software Quality
One interesting part of the presentation was research showing that AI coding tools can **significantly increase initial development speed** while introducing **long-term maintenance problems.** The speaker referenced a study of 806 GitHub projects that adopted Cursor, compared against 1,380 similar projects.
One interesting part of the presentation was research showing that AI coding tools can **significantly increase initial development speed** while introducing **long-term maintenance problems.** The speaker referenced a study of **806 GitHub projects** that adopted **Cursor**, compared against **1,380 similar projects**.
The findings presented included:
@ -249,7 +256,7 @@ However, the central question was whether this increased development velocity tr
![Development Velocity vs Delivery of Value](IMG_25717.png)
**Key takeaway:** We should measure AI-assisted development by delivered business value, software quality and maintainability rather than lines of code or commit counts.
> We should measure AI-assisted development by delivered business value, software quality and maintainability rather than lines of code or commit counts.
### 4. Conceptual Entropy: A Hidden Problem in AI Development
@ -289,12 +296,20 @@ He highlighted three interconnected challenges:
**AI can dramatically accelerate software development, but speed without engineering discipline creates new risks.**
- More generated code doesn't automatically mean more business value.
- AI-assisted development can increase technical debt and complexity.
- Specifications and documentation need consistent terminology and structure.
- Human understanding must keep pace with AI-generated complexity.
- Engineering practices must evolve alongside increasingly autonomous AI systems.
The biggest challenge isn't just making AI agents more capable. It's ensuring that **humans can continue to understand, maintain and control the systems those agents help create.**
> The biggest challenge isn't just making AI agents more capable. It's ensuring that **humans can continue to understand, maintain and control the systems those agents help create.**
---

Loading…
Cancel
Save