Our guidance on using LLMs (for technical writing)
The Ritza Handbook advises on using GPT and GenAI models for writing, highlighting benefits like code samples and overcoming writer's block. However, caution is urged against using GPT-generated text in published articles.
Read original articleRitza Handbook provides guidelines on using GPT and GenAI models for writing purposes. While writers are encouraged to utilize these models for learning new technology or technical steps, the handbook emphasizes that GPT-generated text should not be used in published articles. The reasons include the noticeable stylistic differences between human and GPT writing, the increased editing and QA burden, and the risk of relying on GPT for content creation. The handbook suggests that GPT can be beneficial for creating code samples, overcoming writer's block, understanding concepts before explaining them, formatting text, and providing review suggestions. However, it warns against using GPT-generated text as it may not add value for readers who actively use GPT themselves and could potentially impact search engine rankings. The focus remains on creating original content that adds unique value to the audience.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
ChatGPT is hallucinating fake links to its news partners' biggest investigations
ChatGPT by OpenAI generates fake URLs for major news sites, failing to link to correct articles despite promises. Journalists express concerns over reliability and demand transparency due to hallucinated URLs.
Waves of Writing for Google
The article explores the evolution of writing for Google, highlighting shifts from keyword stuffing to user-focused content and AI's impact on writing jobs. Writers are advised to adapt, focus on personal branding, and embrace technology for relevance.
Gemini's data-analyzing abilities aren't as good as Google claims
Google's Gemini 1.5 Pro and 1.5 Flash AI models face scrutiny for poor data analysis performance, struggling with large datasets and complex tasks. Research questions Google's marketing claims, highlighting the need for improved model evaluation.
My finetuned models beat OpenAI's GPT-4
Alex Strick van Linschoten discusses his finetuned models Mistral, Llama3, and Solar LLMs outperforming OpenAI's GPT-4 in accuracy. He emphasizes challenges in evaluation, model complexities, and tailored prompts' importance.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
ChatGPT is hallucinating fake links to its news partners' biggest investigations
ChatGPT by OpenAI generates fake URLs for major news sites, failing to link to correct articles despite promises. Journalists express concerns over reliability and demand transparency due to hallucinated URLs.
Waves of Writing for Google
The article explores the evolution of writing for Google, highlighting shifts from keyword stuffing to user-focused content and AI's impact on writing jobs. Writers are advised to adapt, focus on personal branding, and embrace technology for relevance.
Gemini's data-analyzing abilities aren't as good as Google claims
Google's Gemini 1.5 Pro and 1.5 Flash AI models face scrutiny for poor data analysis performance, struggling with large datasets and complex tasks. Research questions Google's marketing claims, highlighting the need for improved model evaluation.
My finetuned models beat OpenAI's GPT-4
Alex Strick van Linschoten discusses his finetuned models Mistral, Llama3, and Solar LLMs outperforming OpenAI's GPT-4 in accuracy. He emphasizes challenges in evaluation, model complexities, and tailored prompts' importance.