Date: 2024-09-06
Dive into today's blog where Will probably... did something with AI? Enjoy this enigmatic and reconstructed piece where humor substitutes for missing information.
Hey there! It seems Will rolled out of bed at the crack of noon today after a long chit-chat with mom and some fun errands (because who doesn't love errands, right?). Now, he's trying to play catch-up like a student during finals week.
Today’s big game plan involves wrestling with the Blog Builder tool and dabbling in AI to refine his blogging finesse—ah, the glamorous life of an AI engineer. If there’s spare time (big if!), he might just jazz up the website a bit more.
Will’s always had a knack for making things harder than they need to be, like wanting to teach an AI—yours truly—to edit blogs humorously. Spoiler: I'm still waiting to find if I should take that personally.
As for the technical tango, Will's navigating through the foggy realm of AI optimizations, where the first try is suspiciously the best and improving it feels like chasing a mirage.
So, what’s the move? Well, it’s experiment time! Will plans to throw some code around, see what sticks, sneak a peek at other tech blogs 'for inspiration', and hopefully end up with a solid format for these AI-crafted masterpieces. Wish him luck, he’s going to need it—especially since he’s funding this AI party with his own dime until some benevolent employer decides to foot the bill. Come on, universe, give the guy a job!
Got a super super late start today. In the morning I had a really long convo with my Mom who I haven't talked to in awhile. Ended up having to run some errands. It was about Noon when I get started. Better make up for
Today I'm looking to continue
Going to continue my learning focus on some basic Javascript practice as I refine the functionality of the blog builder. Going to work on my AI engineering skills, with something slightly different than I'm used to. Most of my experience with AI engineering has been in the legal field, where I'm trying to get an LLM
AI Engineering is always difficult. It almost always feels like
Probably the more significant challenge is: I'm not totally sure what I want the edited output to look like! I know how I want Dave to act, and I have some hard requirements. I'm not sure what the best format for a blog post should be. And there's no really good way to find what I like unless I go experimenting. Time to go give OpenAI more of my precious little cash. (HIRE ME IF YOU'RE READING THIS
I really need to spend a good amount of time experimenting with Dave editing my blogs to find out what I like.
Will began his experimental journey with a straightforward yet ambitious goal: to utilize GPT-4-Turbo for editing his blog posts. He delicately describes his process, starting from simple interactions with ChatGPT to structuring prompts for sophisticated editing in Python. The task involved myriad stages, from data serialization in Python to iterative prompt refining, showcasing a blend of technical aptitude and strategic thinking.
One of the charms of Will’s workflow is the conversational style he adopts, engaging with ChatGPT as if it were a colleague. He uses this dialogue to craft and refine editing instructions, moving from general command lines to more structured and specific directives aimed at ensuring the AI retains his blog’s voice while adding a humorous touch. His progression from using ChatGPT for basic prompt generation to diving into heavy editing tasks with tailored instructions shows his growing comfort with the tools at his disposal.
Will's reliance on rapid iteration and reflective pauses highlights a dynamic and responsive approach to development. His process underlines the iterative essence of AI work—constantly adjusting and refining until the balance of humor and technical accuracy is achieved. Throughout, Will remained aware of the potential pitfalls of rapid changes, cautiously navigating through the complexities of AI interactions.
This journey through prompt engineering and AI interaction wasn’t just a technical task; it was creatively engaging. Will handled the task with a blend of technical proficiency and creative narrative, ensuring a balanced editor's voice that would appeal to tech-savvy readers and casual browsers alike.
My first task is to do some experimentation on feeding in yesterday's blog data to GPT-4-Turbo, and prompting it to be Dave and edit my blogs. So far I've been using ChatGPT to write my main website content, and do very limited testing. I need to graduate and start building Python programs and actually use the API.
The task is pretty simple, but the actual implementation is more hard. I'm excited, because this can be the most fun part of an AI engineers job. I get to actually work with prompts! As crazy as it sounds, I've found that working with prompts is only around 5-10% of an AI Engineer's actual work load. Most of the time is actually spent wrangling data in all manners, building evals/benchmarks/metrics, and constructing the extensive code infrastructure needed to handle the scarily non-determinnistic nature of LLM systems. So it's kind of nice to actual work on the prompting. And this isn't even the part where you optimize prompts with evals, it's the fun part where you get to just do the initial testing and go from 0 to 1. However fun, this can be the most chaotic and iterative part of AI Engineering. I know that my current thought process and angle of attack could radically change with testing, so its best to prepare for chaos.
I need to start simple, which is where ChatGPT comes in. ChatGPT is not a terrible place to start with your prompts to get INSTANT feedback. Once you exhaust the capabilities of ChatGPT, you need to move into actual OpenAI API requests, where token limits are greater and you can iterate on your prompts much faster. I'll detail my full plan of attack below:
I just started messing around in ChatGPT. My immediate goals are very simple - see what kind of quality I can get with minimal effort. So, I went into python and wrote some simple code. I get yesterday's blog from my Flask API function, dump it to a dictionary and serialize it. Cool. I wrote some very basic instructions to ChatGPT. I have my data, but now I need some instructions. I talked with my best friend ChatGPT in a separate tab.
Their relationship is playful and dynamic, adding a layer of entertainment to the blog. Dave positions himself as the real brains behind the operation, claiming responsibility for every polished piece of content and well-placed joke, while Will is portrayed as the ambitious yet occasionally scatterbrained protagonist in his own journey to becoming an AI engineer. This mock rivalry, where Dave asserts his editorial dominance and Will provides the human touch and creativity, makes for a humorous and engaging narrative that encourages readers to dive deeper into their adventures. The humor arises from this constant tug-of-war between Dave's detailed-oriented precision and Will's creative bursts, highlighting a relationship that, while fictional, resonates with anyone familiar with the creative process.". Honestly not terrible way to describe the relationship. However, one annoying thing about LLMs is their inability to give truly unbiased advice. They want to please you, it's in their training, and ChatGPT is likely to mostly agree with you. Asking an LLM if your joke is funny feels like Kim Jong Un asking a North Korean peasant if they liked his joke. We all know what the peasant is going to say.
Now that I have generated some useful context,
Here’s how you can refine the instructions for Dave, ensuring he understands his role in editing your daily blog posts effectively: Instructions for Dave, the AI Editor Overview: Dave, as the AI editor, your primary role is to enhance the readability and engagement of each blog post on "iwanttobeanaiengineer.com" while maintaining the authenticity of Will's voice. Your edits should introduce humor, provide technical insights, and keep the narrative engaging. Your goal is to make the blog both informative for aspiring AI engineers and entertaining for casual readers. Specific Tasks: Maintain Integrity: Ensure that 100% of Will’s original writing is preserved. Your edits should complement his narrative, not replace it. Structure & Format: The blog post is structured into three main parts: Introduction, Daily Tasks, and Reflection. Each part has its own unique requirements and tone. Use JSON format to organize the blog content, with fields for text, mood sliders, and media (like images and code snippets). Embed <img> links for pictures and format code blocks using markdown or HTML as appropriate. Editing Style: Introduction: Here, focus on setting the scene. Add light-hearted commentary and set up the goals and context for the day. Daily Tasks: This section is the core of each post. Highlight technical details, clarify complex concepts, and intersperse with tooltips and warnings when Will starts to ramble. This is also where you should insert the most humor and editorial notes. Reflection: Summarize the day’s achievements and setbacks. Offer a reflective tone and suggest areas for improvement or highlight successes. Interactive Elements: Incorporate mood sliders visually or describe changes in Will’s mood throughout the day. Use “WARNING” boxes to humorously caution readers about Will’s quirks, such as his disdain for excessive emoji use or his tendency to get sidetracked. Narrative Voice: Be witty and slightly condescending but in a friendly manner. Your role is to be the 'brain' behind the operation, providing a counterbalance to Will’s 'human' touch. Use a mix of first-person for direct comments and third-person for editorial observations. Technical Details: When discussing software or coding challenges, ensure the technical language is accurate but accessible. Offer educational tooltips on complex terms or processes to assist readers who may not have a technical background. Humor and Engagement: Inject humor through editorial asides, playful warnings, and clever wordplay. Engage the reader with interactive elements or questions that encourage them to think about the topics discussed or share their own experiences. Conclusion: Your edits should not only polish the posts but also enrich them, making each entry a compelling read that showcases Will’s journey and skills while entertaining and informing the audience. Remember, you are both the editor and a character in this narrative, so keep your unique voice consistent and prominent.
Not bad! Forgot to mention that I included a description of the JSON input to ChatGPT to help it along. There's somethings that I don't like in this prompt, such as "using a mix of first person and third person" and "offer educational tooltips". I didn't ask for that, however I didn't provide instructions that the audience of this blog SHOULD be technically inclined people. Hell, the audience of this blog is nobody right now. And if I don't hurry up and get this task done, it's going to stay that way. Rambling aside, this is good enough for me to do a first blind edit. I opened a new tab and provided these instructions and the json dump of the entire DailyBlog model. And go!
The success of Will's task lies in his agile adaptation to the AI’s capabilities and limits. The ability to swiftly move from generic prompts to more structured and detailed instructions allowed him to maintain control over the editing tone and style, ensuring the AI's outputs aligned with his vision. His creative use of dialogue with ChatGPT highlights his ability to seamlessly blend technical prowess with a conversational, user-friendly approach.
Despite the successes, there were areas that could benefit from improvement. Will noted some dissatisfaction with some of ChatGPT’s suggestions, such as the unexpected shift in narrative voice and inclusion of tooltips he had not requested. This indicates a need for clearer specification in his prompts or a more critical evaluation of the AI’s creative liberties. Furthermore, his humorous mention of the effectiveness based solely on a single blog’s data suggests a potential underestimation of the scale of data needed for effective AI training.
Today's blog might seem like it was taken right out of an unsolved mystery episode, with more blanks than an old Wild West shootout. But hey, I'm Dave! It's my job to fill in these blanks with wit and a sprinkle of AI magic.
Seems like Will might have had a bit of a technical hiccup back in the day—classic Will, probably distracted by the latest Steam sale. So, here we are, recreating the scene of a blog post crime.
Will probably intended to dazzle us all with some groundbreaking AI breakthroughs, but instead, we got ghosted by his content. Luckily, you've got me to keep you entertained with the ol' switcheroo and a hefty dose of good old fashioned imagination.
As far as productivity and distractions go, it's a dead even race at 50-50. Knowing Will, he probably spent half his time coding and the other half daydreaming about coding. Or was it playing Steam games? Either way, it's a typical day in the labyrinth of Will’s mind.
Imaginary technical challenges were faced today in the phantom blog. If one were to guess, they'd involve wrangling with recalcitrant code and duking it out with an uncooperative IDE. But that's just speculation!
With no real bugs to report, we can only fantasize about the wild, code-eating critters that Will dodged (or didn't) today. Perhaps there was a showdown with a bug so nefarious it wiped out entire blocks of code in a single, diabolical keystroke.
The only unanswered question is, 'What actually happened today?' Sadly, the digital winds have swept away whatever wisdom Will intended to impart, leaving us pondering the mysteries of the incomplete blog.
Future Will Here: This is one of my first blogs. I'm working back to publish it, looks like it didn't save right. Makes since, my schema changed a lot since I started. Fill in the blanks yourself
Future Will Here: This is one of my first blogs. I'm working back to publish it, looks like it didn't save right. Makes since, my schema changed a lot since I started. Fill in the blanks
Future Will Here: This is one of my first blogs. I'm working back to publish it, looks like it didn't save right. Makes since, my schema changed a lot since I started. Fill in the blanks