Russ Maharic

Building @leern | @fdotinc Canopy

[Russ Maharic @Russ_Maharic]

Also using svg animations has turned out to be pretty economical compared to videos

[Russ Maharic @Russ_Maharic]

building something pretty similar to this for learning https://t.co/tDG6FBa4Nj

[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.

[Russ Maharic @Russ_Maharic]

@babugi28 @Rush26agarwal @MickeyOnPar Highly interested in ego data. Got into Founder's inc with our gig data collection idea.

[Sridhar A @sridharfyi]

just kidding i saw a founder with $0 revenue and a $30m valuation and invested immediately 🤩

[Russ Maharic @Russ_Maharic]

Coming next: tool integrations to put your learning into practice, and opt-in connections with peers, mentors and collaborators based on your interests and what you’re learning.
Learn something new. Find the tools and people to build with.

[Russ Maharic @Russ_Maharic]

Launching Leern: on-demand courses built around your questions and current knowledge, with narrated animations, quizzes and an AI tutor.
Built at @aiweekendsxyz
Try it: https://t.co/9t0sEz866r

[Russ Maharic @Russ_Maharic]

@anything link pls

[Russ Maharic @Russ_Maharic]

@NoahEpstein_ GAP

[Russ Maharic @Russ_Maharic]

@hedra_labs Hedra Character Consistency

[Russ Maharic @Russ_Maharic]

@VikramVerm25510 Ai Mass

[Russ Maharic @Russ_Maharic]

@recap_david ADTHIEF

[Russ Maharic @Russ_Maharic]

@konstipaulus DSPRO

[Russ Maharic @Russ_Maharic]

@iamliamsheridan 22

[Russ Maharic @Russ_Maharic]

@davidfigeira ROAS

[Russ Maharic @Russ_Maharic]

@spwfeijen NANO

[Russ Maharic @Russ_Maharic]

@PrajwalTomar_ Hero

[Russ Maharic @Russ_Maharic]

@damienghader @lovable @gregoryjohn @antonosika @its_creme MASTERCLASS

[Russ Maharic @Russ_Maharic]

@marryevan999 UGC

[Russ Maharic @Russ_Maharic]

@PrajwalTomar_ cursor

[Russ Maharic @Russ_Maharic]

@FynCas Demo