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.
I used to be a normal guy who posted about ML on Twitter.
Then Israel came, and my posts became political.
Then Argentina came, and my posts became about sports.
Can you please tone down your genocide and your genocide-washing, so I can go back to posting about linear regression?
If they can eliminate Ali Khamenei with surgical precision, why did they have to bomb the classrooms? Why murder the kids?
I didnโt want to return to this space. But after seeing over 80 schoolgirls killed today, hearing their families scream as they search frantically through rubble, I was pulled straight back to Gaza. There is something uniquely horrific about the killing of children.
At what point do we stop pretending this is collateral damage and recognize it clearly as the preferred tactic of the Jewish state?
Thereโs nothing I can say that hasnโt already been said. Iโm not a reporter. Iโm not a journalist. And none of this came as a surprise.
This is a war that Netanyahu himself openly demanded for decades. The escalation didnโt fall from the sky. It was built, speech by speech, policy by policy, threat by threat.
Everyone had the opportunity to make noise. To resist and refuse it. And yet here we are.
I donโt have analysis to offer. I have grief. And anger. And a refusal to pretend this was inevitable.
May Iran prevail against the enemies of humanity, and may Israel collapse into hell where they can finally meet their lord Baโal and face the consequence of their devotion.