We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
@HBOMaxHelp Dear intern,
It’s ok. I dropped a prod database when I was a senior engineer. These things happen more often than you might think. Building good systems is about having resilience against human mistakes. Because we, humans, always make mistakes.
Product Thinking -- Why it matters, what it is, what it isn't, and how you improve your skills.
aka: "Look Ma, I wrote an article instead of a tweet thread!"
https://t.co/maB0JrDJyr
"How can we, a smaller company, compete with larger ones that pay better, for software engineers?"
My take:
1. Try to pay better
2. Regardless if you do, improve your hiring process. Everyone talks about hiring being broken: here are things you can do.
What am I missing?
We're thrilled to have won two awards at #etawards19! Read our latest blog post to learn how our #eventapp keeps improving the event experience for busy organizers and attendees. https://t.co/0Odh4UFNWX
ACM FCRC (13 conferences including ISCA/PLDI/ICS/SIGMETRICS/STOC/) is using Whova app to navigate and find people in this massive event. Download Whova and get into the event with invitation code from FCRC in your email. https://t.co/DY8BwDMN7d
Are you organizing your company's internal meetings or customer/partner conferences? Check this case study to see how Whova has helped corporate events: https://t.co/fXklVW5MKI #eventtech#eventprofs
I have a super-talented friend who is a @ucsd_cse alum & also the co-founder of Whova 🥳 AAAAANNDD they are hiring Backend Software Engineers in the pretty city of San Diego 🏖️ HMU for details !
RT pls, we never who we might end up helping 😉
https://t.co/S7yMc2WwDN