True. One trick that works when reviewing PR created by LLMs:
Make the PR template require a "Judgment calls" section. Understanding gap comes from decisions LLM made that you didn't specify. Have them list each one and where to look. It makes PR review quick and efficient.
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.
A not-so-popular metric that you would want to measure with your product / feature launches is customer service contacts ππ¬ #CustomerService#customersupport
NeurIPS π―π!
βall come all servedβ
Registration is $25 for students and $100 for non-students.
Tutorials, keynotes and oral pre-recorded presentations accessible without a registration. Video recordings of the poster presentations will be released after the conference.
Tired and hungry people make bad decisions!
- @kahneman_daniel (From the book "Thinking, Fast and Slow")
Make sure you are well fed before you make an important decision next time.
Hey fellow @ApacheSpark developers!
Found an unusual partitioning behavior when cross-joining large DataFrames. Didn't find documentation about it in @ApacheSpark official docs, so wrote a blog post about it. Do check it out at https://t.co/D6GnG8lHDd. #Spark#BigData
This is "Pudi Dosa" at MTR tiffin's, Singapore. It's the best dosa I ever had. If you visit little India in Singapore, I highly recommend going to MTR tiffin and having Pudi Dosa. The mixture of spices and Ghee that's applied on top of the dosa is what makes this dosa so unique.