Bethylogism

Syllogisms, but... Bether. Philosopher/neuroscientist turned software engineer (React/Native).

[Bethylogism @bethylogism]

don't know why but i find this rly adorable. like it's saying "oh noeee, get me outta here"

[Andrej Karpathy @karpathy]

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less "two groups of people speaking past each other" and more a sharp funnel.

- Napkin math somewhere around 6B people (~75% of the population) have barely come in contact with LLMs at all.
- Around 1-2B (~20%) are casual and infrequent users of free-tier ChatGPT-like products. This group sees derpy chatbots and treats them a bit like a better Google search, a writing aid, or etc. Maybe an agent tries to book you a flight. I have non-tech friends who (reasonably, imo) say they have not much use for it at all. Even many professionals outside of math&code are in this tier. For example, execs and many other functions spend a lot of their time talking to other people, so while they understand what is happening intellectually, it is still second-hand and a bit abstract.
- Now we get to professional use of frontier-grade LLMs in math&code. Somewhere around 20M people (0.2%) see first-hand that large, complex projects that used to take them weeks/months can now be completed by agents with a prompt. Building apps, copying apps, translating apps, decompiling apps from binaries... This has all happened very quickly and recently - less than 1 year ago, I was writing code manually by hand, typing memorized computer code commands into a code editor character by character, occasionally pressing Tab to autocomplete a little chunk of code.
- And finally we get to the ~5,000 people (~0.00006%) with access to frontier-grade systems internally. The external world has seen the preview. It looks like swarms of thousands of agents collaborating over weeks on software mega projects: minting zero days, running cyber attacks and defenses at machine speeds, discovering new science, advancing the frontier of mathematics. Things that would have taken top professionals in the industry years of work. Meanwhile, human review and comprehension are starting to fall behind. For example, people are still involved in the "archeology" of the OpenAI-HF incident from many months ago. Mathematicians may be poring over the 722 manuscripts on frontier mathematics for a while.

The funnel is driven by a combination of factors:
1. The impact scales with ambition, problem size, and horizon. A question with a paragraph answer barely stresses the system. You need a reservoir of big, difficult problems that you really care about. This aspect drives the consumer / professional dimension of the funnel.
2. The jaggedness of the system (which I have written about a lot separately). Capability peaks in domains that are digital, verifiable and economically valuable. This is because LLM capability emerges from reinforcement learning on verifiable rewards on a curated environment mixture driven by revenue potential. This aspect primarily drives the area (e.g. math&code) dimension of the funnel.
3. Access. Free-tier, paid-tier, internal.

So this is the weirdness of the moment. The general public has mostly not interacted with these systems. When they have, it looks like a derpy chatbot. The majority of professionals still see only a modest uplift. And a small sliver of professionals are experiencing the vertigo of the curve going vertical. And it is all happening at the same time.

[Pierre Ricadat @ghostdogpr]

I applied an idea from @fwbrasil to create my own "refine" skill that reduces code complexity (and size) using an orchestrator agent and 3 subagents iterating on Constraints (Bjarnason), Simplicity (Hickey) and Parametricity (Wadler). Produced design and code looks much better!

[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.

[Bethylogism @bethylogism]

@oNouguier @scala_js @threejs @kilocode trés cool!

[Bethylogism @bethylogism]

2024 me: I'm solving problems, writing code 😎
2025 me: I'm solving problems, pairing on code! Cool.
2026 me: Problems are being solved. Code is happening.

[Bethylogism @bethylogism]

Didn’t even need to change out of beach shorts. Bonus.

[Bethylogism @bethylogism]

Loved getting zen with code at @ReactAlicante this year! And what brilliant energy and vibes this conf always has👾 🫶 🧡

[Frontier Alicante 🧑‍💻🌞🏖️🥘 @FrontierAlicant]

Great start of today's lightning talks with @bethylogism 🧘‍♀️🧘‍♂️

[Frontier Alicante 🧑‍💻🌞🏖️🥘 @FrontierAlicant]

Have you nodded your head at books about clean code, murmured in agreement with articles on encapsulation, but still found yourself shaking your fist at your own name on Git Blame? Join @bethylogism and see how sorting out your code is a bit like sorting out your life. 🧘‍♂️

[Bethylogism @bethylogism]

Big plans. 🖤

https://t.co/OPoZe5UTnt

[Dominik 🔮 @TkDodo]

📚 I love component composition in React, and I think we should use it a lot more before littering our components with conditional renderings for mutually exclusive states. As a follow-up to a tweet from this week, here's the full blogpost:
https://t.co/0YERk0hwyq

[Bethylogism @bethylogism]

Yes, this is JavaScript.

[Bethylogism @bethylogism]

Some absolute gold at @ReactAlicante this year. Can’t wait to make every dream come true with rise tools. (Thanks @EricVicenti)

[Bethylogism @bethylogism]

https://t.co/ddG6Sf8AQM something about this…

[Bethylogism @bethylogism]

Well there's only one thing to be done now isn't there

[Bethylogism @bethylogism]

I’m attending JSNation – the main JavaScript conference of the year. You may join me there for free with 10k other JS engineers and 40+ great speakers. Just follow this badge.

#javascript
https://t.co/CUXDKnOeEH
#jsnation

[Bethylogism @bethylogism]

Hey London peeps, - if any of you are interested in nerding out about JavaScript tonight after work, I'm hosting another ReactJS Girls event at the big Sainsbury's HQ in Holborn! All genders welcome. Grab a free ticket: https://t.co/PBkIalcsuJ