(I'd love to get your feedback!)
- This is something I have found missing in my current workflow when reviewing PR's. Particularly in the age of large AI generated PR's.
I think most reviewers do this to some degree by looking at points of interest. It'd be cool if this could look at your prior reviews and try to learn your style.
Is this the correct commit to look at? https://github.com/manaflow-ai/cmux/commit/661ea617d7b1fd392...
- Last year, I built a DM for myself using the OpenAI api and an elevenLabs voice generator. I asked it set my character in Baldur's Gate, so it could pull upon the huge amount of DnD source material it had been trained on.
A few takeaways:
1. An LLM based DM can give the player essentially infinite richness and description on anything they ask for.
2. There is difficulty in setting the rules for the LLM to follow that match the DnD rulebook. But this is possible to solve for. Also, I found the LLM to be too pliable as a DM. I kept getting my way, or getting my hand held through scenarios. Maybe this is a feature?
3. My conversation quickly began to approach the context window for the LLM and some RAG engineering is very necessary to keep the LLM informed about the key parts of your history.
4. Most importantly, I found that I most enjoy the human connection that I get through DnD and an LLM with a voice doesn't really satisfy that.
- I come back to it from time to time and play for a week. It looks like it's been getting more accessible over time, with a new UI update having been rolled out recently.
There's definitely a certain mindset that helps make it more enjoyable. Imagination being key! From the technical side, the developers have peeled back the curtain on how they've created parts of the game:
https://www.youtube.com/watch?v=U03XXzcThGU&ab_channel=Logo%...
https://www.youtube.com/watch?v=jV-DZqdKlnE&ab_channel=GDC20...
- "Regarding cognition, both groups improved in attention and spatial memory, but no significant group differences emerged."
So, the dance group showed increase volume of brain matter. Is there a benefit to having the extra brain volume, even if it doesn't lead to improved cognition?
Is it possible that increased volume just helped them become better dancers?
- I ran into some scaling challenges with Postgres a few years ago and had to dive into the docs.
While I was mostly living out of the "High Availability, Load Balancing, and Replication" chapter, I couldn't help but poke around and found the docs to be excellent in general. Highly recommend checking them out.
- So in this case we would be eliminating the power of the individual to undertake large, risky undertakings that would provide a net benefit to society.
Now you'd have to cobble together a group of investors, but if you can't find people who don't understand your vision, you're out of luck.
Or you could go to a bank, so now the banks have more power, but they probably won't invest in your risky idea anyway.
Okay so I guess, now it's up to the government to undertake this large risky project? Great.
I don't know, I like the fact that motivated individuals can take a large amount of their own capital and take on large projects.
- On balance, I like Rails because you get so much functionality out of the box.
My biggest concern is that when your project deviates from the happy path of that functionality you've got to invent your own architecture and patterns. Knowing when to create a service objects vs say adding more functionality to a model is an example. In that case, you're out of the land of convention and into the land of opinion.
- > No single change is going to produce AGI. We're going to have a lot of forewarning, and it'll be obvious we're opening Pandora's box.
AutoGPT is an interesting example where an AI system, just by self prompting, led to an order of magnitude increase in (change/productivity/activity), extremely rapidly.
Another perspective where this exact feature would be useful is in security review.
For example - there are many static security analyzers that look for patterns, and they're useful when you break a clearly predefined rule that is well known.
However, there are situations that static tools miss, but a highlight tool like this could help bring a reviewer's eyes to a high risk "area". I.e. scrutinize this code more because it deals with user input information and there is the chance of SQL injection here, etc.
I think that would be very useful as well.