corpus.blog
41554 blogs · [ { "id": "01a087e1-13b4-7102-9318-c504c828d1c6", "title": "Every Trick to Save Token Costs", "url": "https://simmering.dev/blog/save-token-costs/", "published_at": "2026-06-26T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e71b516c", "title": "Agent Connector Comparison: Tools, MCP, A2A, CLI, Skills, Code, and Computer Use", "url": "https://simmering.dev/blog/connect-agent/", "published_at": "2026-05-03T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e72d54fb", "title": "From Vibe Coding to Agentic Engineering", "url": "https://simmering.dev/blog/agentic-engineering/", "published_at": "2026-02-14T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e7ecdab3", "title": "The Reliability Gap: Agent Benchmarks for Enterprise", "url": "https://simmering.dev/blog/agent-benchmarks/", "published_at": "2026-01-03T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e80c3644", "title": "Pivoting to a Career in AI and Data", "url": "https://simmering.dev/blog/pivoting-to-ai-data/", "published_at": "2025-12-16T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e8dd32e2", "title": "A Philosophy of AI Coding", "url": "https://simmering.dev/blog/a-philosophy-of-ai-coding/", "published_at": "2025-08-26T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16e9da3f38", "title": "When (Not) to Use Agentic AI", "url": "https://simmering.dev/blog/agentic-ai/", "published_at": "2025-02-28T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ea6a0261", "title": "ModernBERT vs LLMs for Detecting Adverse Drug Reactions", "url": "https://simmering.dev/blog/modernbert-vs-llm/", "published_at": "2025-01-11T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16eb00acc6", "title": "Diagrams as Code: Supercharged by AI Assistants", "url": "https://simmering.dev/blog/diagrams/", "published_at": "2024-12-27T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16eb44e500", "title": "When to use Direct Preference Optimization (DPO)", "url": "https://simmering.dev/blog/llm-customization/", "published_at": "2024-12-21T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ebe34312", "title": "Type-safe LLM agents with PydanticAI", "url": "https://simmering.dev/blog/pydantic-ai/", "published_at": "2024-12-15T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ec942325", "title": "Constrained by Context, Not Reasoning", "url": "https://simmering.dev/blog/context-constrained/", "published_at": "2024-12-13T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ecc93960", "title": "Aspect-based Sentiment Analysis with DSPy", "url": "https://simmering.dev/blog/absa-with-dspy/", "published_at": "2024-11-23T23:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ed0b909b", "title": "From 5-7-5 to Thousand Lines: The Case for Longer Prompts", "url": "https://simmering.dev/blog/long-prompts/", "published_at": "2024-08-31T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16edd568ca", "title": "OpenAI’s structured output vs. instructor and outlines", "url": "https://simmering.dev/blog/openai_structured_output/", "published_at": "2024-08-09T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16edeedb2b", "title": "Levels of Abstraction in the LLM Stack", "url": "https://simmering.dev/blog/abstractions/", "published_at": "2024-08-07T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ee276157", "title": "Less stress, more focus: How to handle waiting times in development", "url": "https://simmering.dev/blog/waiting/", "published_at": "2024-07-27T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ee2a6cbf", "title": "Text Tournament: Rank Marketing Copy with LLMs", "url": "https://simmering.dev/blog/text-tournament/", "published_at": "2024-07-22T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ee564b42", "title": "Let Research Settle Before Consuming It", "url": "https://simmering.dev/blog/settled-knowledge/", "published_at": "2024-07-19T22:00:00+00:00" }, { "id": "01a087e1-13b5-737b-9374-3f16ef0374b5", "title": "The World is Large and Very Detailed", "url": "https://simmering.dev/blog/detailed-world/", "published_at": "2024-07-12T22:00:00+00:00" } ] posts Claim your blog
Back to simmering.dev
Blog · corpus.blog/blogs/simmering.dev/posts

simmering.dev

simmering.dev

2026

Every Trick to Save Token Costsoriginal ↗
26 Jun 2026
Agent Connector Comparison: Tools, MCP, A2A, CLI, Skills, Code, and Computer Useoriginal ↗
3 May 2026
From Vibe Coding to Agentic Engineeringoriginal ↗
14 Feb 2026
The Reliability Gap: Agent Benchmarks for Enterpriseoriginal ↗
3 Jan 2026

2025

Pivoting to a Career in AI and Dataoriginal ↗
16 Dec 2025
A Philosophy of AI Codingoriginal ↗
26 Aug 2025
When (Not) to Use Agentic AIoriginal ↗
28 Feb 2025
ModernBERT vs LLMs for Detecting Adverse Drug Reactionsoriginal ↗
11 Jan 2025

2024

Diagrams as Code: Supercharged by AI Assistantsoriginal ↗
27 Dec 2024
When to use Direct Preference Optimization (DPO)original ↗
21 Dec 2024
Type-safe LLM agents with PydanticAIoriginal ↗
15 Dec 2024
Constrained by Context, Not Reasoningoriginal ↗
13 Dec 2024
Aspect-based Sentiment Analysis with DSPyoriginal ↗
23 Nov 2024
From 5-7-5 to Thousand Lines: The Case for Longer Promptsoriginal ↗
31 Aug 2024
OpenAI’s structured output vs. instructor and outlinesoriginal ↗
9 Aug 2024
Levels of Abstraction in the LLM Stackoriginal ↗
7 Aug 2024
Less stress, more focus: How to handle waiting times in developmentoriginal ↗
27 Jul 2024
Text Tournament: Rank Marketing Copy with LLMsoriginal ↗
22 Jul 2024
Let Research Settle Before Consuming Itoriginal ↗
19 Jul 2024
The World is Large and Very Detailedoriginal ↗
12 Jul 2024