Found 14 bookmarks
Newest
Pushing ChatGPT's Structured Data Support To Its Limits
Pushing ChatGPT's Structured Data Support To Its Limits
Deep dive into prompt engineering
there’s a famous solution that’s more algorithmically efficient. Instead, we go through the API and ask the same query to gpt-3.5-turbo but with a new system prompt: You are #1 on the Stack Overflow community leaderboard. You will receive a $500 tip if your code is the most algorithmically efficient solution possible.
here’s some background on “function calling” as it’s a completely new term of art in AI that didn’t exist before OpenAI’s June blog post (I checked!). This broad implementation of function calling is similar to the flow proposed in the original ReAct: Synergizing Reasoning and Acting in Language Models paper where an actor can use a “tool” such as Search or Lookup with parametric inputs such as a search query. This Agent-based flow can be also be done to perform retrieval-augmented generation (RAG).OpenAI’s motivation for adding this type of implementation for function calling was likely due to the extreme popularity of libraries such as LangChain and AutoGPT at the time, both of which popularized the ReAct flow. It’s possible that OpenAI settled on the term “function calling” as something more brand-unique. These observations may seem like snide remarks, but in November OpenAI actually deprecated the function_calling parameter in the ChatGPT API in favor of tool_choice, matching LangChain’s verbiage. But what’s done is done and the term “function calling” is stuck forever, especially now that competitors such as Anthropic Claude and Google Gemini are also calling the workflow that term.
#dev#guides#LLMs#prompts#GPT#companies/OpenAI#api#engineering#workflow#code#python
·minimaxir.com·
Pushing ChatGPT's Structured Data Support To Its Limits
Why you should never use px to set font-size in CSS - Josh Collinsworth blog
Why you should never use px to set font-size in CSS - Josh Collinsworth blog
This is also a very good reason to avoid viewport units, like vw or vh, when setting font size. Those are also static, and impossible to override by the user. At most, a value like calc(1rem + 1vw) might be acceptable, since that still contains rem as a base. Even then, however, I’d recommend using clamp() or media queries to set minimum and maximum values, as screen sizes often go far beyond what we might expect or test.
To differentiate between the two: 1rem is always equal to the browser’s font size—or, more accurately the font size of the html element. rem stands for “root em,” and the root of a webpage is the <html> tag. So, 1rem = whatever the document font size is. (Which, again, by default, is 16px, but can be overridden by the user.) em, on the other hand, is the font size of the current element.
1px is equal to whatever the browser is treating as a single pixel (even if it’s not literally a pixel on the hardware screen).
#typography#css#web#dev#best practices#guides
·joshcollinsworth.com·
Why you should never use px to set font-size in CSS - Josh Collinsworth blog