The music for that episode still takes me galaxies/dimensions away

https://youtu.be/IYpO3EbvMK4?si=n70N7hi8v29NiZvr

I think Discord performs great

As an Unreal game dev what I’ve wanted to remake in QT is the Epic Games Launcher.

I think Epic may be underway on this now but if you did a good enough job I feel like there may still be a window to pitch them on acquiring your work.

You will still get hallucinations. With RAG you use the vectors to aid in finding things that are relevant, and then you typically also have the raw text data stored as well. This allows you to theoretically have LLM outputs grounded in the truth of the documents. Depending on implementation, you can also make the LLM cite the sources (filename, chunk, etc).

The approach that has worked for us in production is correction during generation, not after.

The model verifies its output against the rules in the prompt as it generates and corrects itself within the same API call — no retries, no external validator. If there are still failures the model cannot fix at runtime, those are explicitly flagged instead of silently producing wrong output.

This does not mean hallucinations are completely solved. It turns them into a measurable engineering problem. You know your error rate, you know which outputs failed, and you can drive that rate down over time with better rules. The system can also self-learn and self-improve over time to deliver better accuracy.

I’m still learning this advantages and differences between them, would there be benefits to SFT and RAG? Or does RAG make SFT redundant?

I think generally, SFT is like giving the LLM increased intuition in specific areas. If you combine this with RAG, it should improve the performance or accuracy. Sort of like being a lawyer and knowing something is against the law by intuition, but needing the library to cite a specific case or statute as to why.

Thank you I appreciate the reply and that analogy helps make sense of this.

Absolutely not sounds like a be careful what you wish for Black Mirror episode where you wake up trapped in some simulation you can’t break free from but it’s ok because you signed on the dotted line to donate your mind and body to science.

What are we going to do about software for critical infrastructure in the coming decade?

Feels inevitable that code for aviation will slowly rot from the same forces at play but with lethal results.

It will be written much the same as now, but using AI to improve quality through code inspection etc.

Just because nearly all software is going to be written by AI, does not mean critical infrastructure will be.

At some point people are going to start asking why software that doesn't need to be right should exist in the first place

I’m not sure I follow, but I don’t hear anyone asking those questions of the bad software we already have today.

Cabin in the woods.

Curious if you could try to explain it. It’s my goal to sit down with it and attempt to understand it intuitively.

Karpathy says if you want to truly understand something then you also have to attempt to teach it to someone else ha

Yes, that’s true! That could be my next step… though I have to admit, writing this in a HN comment feels like a bit of a challenge.

>> That deep, focused, creative problem-solving where hours disappear and you emerge with something you built and understand.

Yea but for how long? Go back and read any code you wrote a year ago and realize it could have been AI that wrote it.

Ha funny I had a similar idea I was calling ‘GameFlock’ but game date is much better.

To the creators I think there is something here worth continuing to push and try to find traction. As a game developer this is just a matchmaking algorithm with a week to month long wait time :)

My plan was to try to prime the pump with a few popular games and reaching out to existing communities to make them aware and possibly help organize the software/tools to help onboard new players.

For example Ultima Online has Outlands. Tribes2 has a popular discord that arranges matches. I imagine WoW classic and I know C&C Generals have active communities on Discord and I think they’d be willing to work with you to help prime the pump.

Then once you’ve got that critical mass of usage hope that players will participate in other games outside their main passion to make other game dates a success.