LLM

Latest developments

How To Write With An LLM Simon Willison’s Weblog · 6 days ago · 30

Perplexity’s new agent runs entirely on your GPU — with one expensive catch The New Stack · 1 week ago · 18

Why basic RAG fails at multi-hop reasoning (and how GraphRAG fixes it) The New Stack · 4 weeks ago · 21

The End of No Code exe.dev · 1 month ago · 21

TutorMoments: Do AI tutors know when to help and when to hold back? Allen Institute (AI2) · 1 month ago · 41

Q3 2026

◆ Perplexity adds a local “Portable Computer” agent to its Windows app for compatible NVIDIA RTX PCs with 24GB+ VRAM Deployment

◆ Allen Institute releases TutorMoments framework evaluating LLM ability to balance pedagogical scaffolding and cognitive rigor in math tutoring Research publication

• 17 Sep How To Write With An LLM
• 14 Sep Perplexity’s new agent runs entirely on your GPU — with one expensive catch
• 27 Aug Why basic RAG fails at multi-hop reasoning (and how GraphRAG fixes it)
• 7 Aug The End of No Code
• 7 Aug TutorMoments: Do AI tutors know when to help and when to hold back?

Relationships

Products & technology

• Thomas Ptacek deploys this technology · 1 source