terminal
howtonotcode.com

Stories by Tags

Search and filter stories across all digests by tags. Stories must match all selected tags.

rag close rag close rag close
view_list All wb_sunny Daily calendar_today Weekly
sell python (32) sell sdlc (28) sell code-generation (26) sell anthropic (11) sell claude-code (10) sell github-copilot (8) sell claude (7) sell google-gemini (6) sell openai (6) sell vscode (6) sell ci-cd (4) sell code-review (4) sell cursor (4) sell zhipuai (4) sell agents (3) sell ai-agents (3) sell ci/cd (3) sell glm (3) sell glm-4.7 (3) sell prompt-engineering (3) sell sql (3) sell testing (3) sell ai-governance (2) sell chatgpt (2) sell gemini (2) sell git (2) sell github (2) sell google-ai-studio (2) sell llm-evaluation (2) sell minimax (2) sell model-evaluation (2) sell model-serving (2) sell nvidia-nemotron (2) sell rag sell vertex-ai (2) sell windsurf (2) sell agentic-ai (1) sell agentic-workflows (1) sell ai-code-assistant (1) sell ai-evaluation (1) sell ai-generated-code (1) sell ai-ide (1) sell android (1) sell anysphere (1) sell apache-airflow (1) sell api-security (1) sell atlas (1) sell benchmarking (1) sell claude-3-5-sonnet (1) sell codeium (1)

Stories with tags: rag, rag, rag

Showing 1-2 of 2

NotebookLM adds structured data tables; Gemini 3 upgrade reported

article Daily Digest calendar_today 2025-12-25 Daily
sell notebooklm sell gemini sell google-sheets sell rag sell sdlc

Two creator videos report that Google NotebookLM now supports structured data tables and has been upgraded to Gemini 3. If accurate, this should improve table-aware reasoning and make it easier to analyze spreadsheets/CSVs directly inside NotebookLM; confirm details in official docs before relying o...

Read Full Story arrow_forward

Prioritize small, fast LLMs for production; reserve frontier models for edge cases

article Daily Digest calendar_today 2025-12-25 Daily
sell openai sell python sell model-routing sell rag sell cost-optimization

A recent analysis argues that fast, low-cost "flash" models will beat frontier models for many production workloads by 2026 due to latency SLOs and total cost. For backend/data engineering, pairing smaller models with retrieval, tools, and caching can meet quality bars for tasks like SQL generation,...

Read Full Story arrow_forward