RYAN retweeted
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.
RYAN retweeted
あなたが1日で作れたそのゲーム、たぶん「回って」いません。
AI×ゲーム開発のニュースをよく見かけるようになりました。私自身、ゲーム開発でAIはどんどん駆使すればいいと思っています。
ただ、「AIで作ったゲーム」として流れてくるものを見ると、何かのコピーでしかないものが多いんですよね。
「ソウルライク、1日で作れた」
「Only Upを数行で作った」
最新モデルの検証としては分かります。でも、これはゲームを作ったことにはなりません。
実際、インゲームの部分はAIで割とささっと作れます。「それっぽい」し、「ちゃんと動く」ので、「ゲームっぽい」んです。
ただ、遊んでみると「ゲームになっていない」ことがわかります。
ゲームは大きくインゲームとアウトゲームに分かれています。アクションRPGなら、フィールドを歩いたり戦ったりするのがインゲーム。装備やスキルの設定、クエストの管理などがアウトゲームです。
「ゲームになっていない」ものは、インゲームに向かわせる強い誘引が、アウトゲーム側に設計されていません。
だから、遊んでいてこうなります。
「何のために敵を倒すの？」
「うん、だから何？3回やったら飽きるんだけど」
そして、肝心のインゲームのほうも、動かしていてあまり気持ちよくない。
「動きはする」けれど、「気持ちよくない」。
ここが一番の差だと思っています。
「どうすれば気持ちよくなるのか」
「どうすればもっと戦いたくなるのか」
これを設計するのが、ゲームづくりです。
そして面白いのは、断片を作るコストが下がるほど、それを繋いで回す仕事の価値は上がります。
プランナーの仕事は、まだまだなくなりません。
Starting a new company: Vanilla Ice Games. Theirs goes “it’s a me, Mario” our goes “it’s, uh, me Mario” it’s not the same.
Had a chat with some friends about AI. They all believe its going in the negative direction and that nobody is working on things we actually need. Is anyone out there working on something like curing diseases, discovery, etc and operation as a solo or small team? I want to broaden my circle.
There’s an interesting dilemma right now where you can start a project, where it will take you 3 months to make it good enough for people to be impressed, or you can do nothing for 2 months and get all that work done in a day with the newer models
Back in the 1950s science fiction was writing about 2026. Now science fiction is only predicting a year away. I wonder if that gap will close to 0.
Here's a game I've been working on. It's a tower defense where you get 5 units that you permanently level up and progress, each with an infinitely customizable passive tree (Think cluster jewels from POE... it's all cluster jewels). It's built with Astra with LOVE2D.
RYAN retweeted
I’m crying of laughter - please let this be the model that solved Navier-Stokes
(this guy’s name is hayZee, we need to get him on here!)
People are running out of credits quickly with godot and blender. But I’m finding success making 3d games in Love2d and it doesn’t use any credits, like I can’t spend them fast enough before I get reset
RYAN retweeted
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
I created a synthetic population of 5000 americans and a polling app where you can ask them any question you construct as a multiple choice. I fed in Trump's AI rebranding question (but included Artificial Intelligence as a 4th option). The population then answers the question with jev. Artificial Intelligence scored 90% and Superior Intelligence scored 8%.
RYAN retweeted
I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations.
I hooked it up to web search, wikipedia, weather, todoist and home assistant.
Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!
We should shut down Anthropic and OpenAI completely over the doomerism and watch how quickly they switch to “It was just a marketing strategy!”
People are pushing all this AI fear, but the only real evidence we have so far is good, good, good. Let me know when something bad happens. Until then I’ll promote pushing it forward
I think I could build in LOVE2D indefinitely using Astra. It basically consumes no credits and still puts out high quality work.