Rob B.

[Rob B. @robbechamp]

@alanhoward @OpenBot_ Just cancelled grokbot super subscription, moving to Openbot with my existing OpenAI subscription today. Will let you know how it goes...one thing's for sure, grokbot now unusable about it was nerfed. Time to move on :)

[Rob B. @robbechamp]

@Rahmanbarik Yup

[Rob B. @robbechamp]

@bruno_munhoz Haha doing the same thing

[Rob B. @robbechamp]

@melvindvivas Nothing, I hit my usage limit 2 days ago

[Rob B. @robbechamp]

@johnaspinallai @eulahwu971 @spacexai @poteto lol I hear ya…and dots is absolute dogshit

[Rob B. @robbechamp]

@TylerDurden Must have cost you a fortune using grokbot

[Ryan Evans @ry_d_e]

Zuck this morning.

[Rob B. @robbechamp]

@elonmusk @bot Great product but costs are excessive for average user. Highly recommend to those with cash to burn though!

[Rob B. @robbechamp]

@ArgileNoland Same issue and outcome for me

[Rob B. @robbechamp]

@realbeandog @distortgeekin agreed - i'm in the "super" subscription and still not enough ... this may be a deal breaker for grokbot.

[vittorio @IterIntellectus]

how can you tell if a society is collapsing?

[Andrej Karpathy @karpathy]

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.

[ALX 🇺🇸 @alx]

Hillary Clinton wanted to drone strike Julian Assange.

[Frank Grimes Jr. @FrankGrimes_Jr]

There's a lot of talk it's because Canada banned plastic grocery bags

[Millennial Grump @mapleblooded]

If we have no one to sell $4.2 billion in potash to annually and our oil stays in the ground all Canada will have left to produce is our sense of moral superiority.

[Rob B. @robbechamp]

@Rachaelmar1e @JulianAssange 🤡

[Rob B. @robbechamp]

@unusual_whales 😂

[Directive Creator 🪥 @Escapation]

We Must Pace the Frontier

[Rob B. @robbechamp]

@AlexFinn Bro you must be so damned rich … how can you afford all this stuff

[Rob B. @robbechamp]

@udiWertheimer @AlexFinn 😂