14,962
edits
LLMs Usage FAQ: Difference between revisions
Jump to navigation
Jump to search
m
→Same Model, But Does It Behave Differently via API vs. Web Interface (Subscription)?
| Line 303: | Line 303: | ||
# Conversation Memory: For plain text conversations, a key difference is how context (conversation memory) is handled — the web interface manages it automatically on the provider's end, while the API requires developers to manage it themselves. | # Conversation Memory: For plain text conversations, a key difference is how context (conversation memory) is handled — the web interface manages it automatically on the provider's end, while the API requires developers to manage it themselves. | ||
# System Prompt: The web interface (e.g., Claude.ai) uses a system prompt maintained and regularly updated by Anthropic<ref>[https://platform.claude.com/docs/en/release-notes/system-prompts System Prompts - Claude API Docs]</ref>; with the API, the system prompt is entirely up to the developer. | # System Prompt: The web interface (e.g., Claude.ai) uses a system prompt maintained and regularly updated by Anthropic<ref>[https://platform.claude.com/docs/en/release-notes/system-prompts System Prompts - Claude API Docs]</ref>; with the API, the system prompt is entirely up to the developer. | ||
== How to Get Started with AI-Assisted Refactoring of Legacy Code? == | |||
📝 Question: I'm responsible for maintaining a system that has been running for over a decade, and my manager has directed me to adopt AI-assisted development tools to refactor the existing codebase. As a relatively junior lead with limited experience in agentic AI tools, I need to guide other junior team members through this initiative — all without external consulting support. How should I effectively approach and drive this forward? | |||
💬 Answer: | |||
Two talks in Mandarin from WebConf are well worth referencing: | |||
The first one is directly on point — the speaker shares a hands-on refactoring journey spanning decades of legacy system work, with collaborative notes and slides available. Although AI coding tools were part of the picture, the core message is that refactoring is fundamentally a software engineering discipline. | |||
The second talk, despite its business-focused title, mirrors your situation closely — a manager hands down a refactoring mandate. The speaker takes a pragmatic angle: given limited development time and resources, rather than rewriting everything one-to-one, start by embedding logs in the legacy system to gather data on which features are actually being used. Then use that usage data to make the case to your manager and other stakeholders that a full rewrite isn't necessary. | |||
Together, these two talks cover the two core challenges you're facing: start with the business mindset, then figure out how to execute. | |||
# Rescuing Legacy Code in the Age of AI — https://webconf.tw/speakers/39 | |||
# Living in the Best Era for Tech Workers: Using Business Thinking to Optimize Your Life Choices — https://webconf.tw/speakers/18 | |||
== Related articles == | == Related articles == | ||