faizshah

I think when I saw word2vec I realized that semantic meaning can be encoded in machines just from prediction. So then when seq2seq etc came around I saw that this encoding could be used to make increasingly more convincing imitations of thought and language.

I think what wasnt obvious was when Transformers came around it wasn’t obvious that generating text could get comparable results to thinking. So when Chain of Thought etc came around it was really surprising but ReAct arch made it obvious that some control loops would be the next stage.

I think now working with big multi agent systems with Opus 5.5 its clear once we develop the right mainframe-y sorta infra (virtual filesystems, deeper tool permissions, file locking, agent metrics, etc) there is a clear path emerging to what the future of the industry will look like (imo).

It's not just obscurity, it's increasingly difficult to trust the governance and quality of code of any outside library. A lot of deps in code are unnecessary you use maybe 1-10% of the api surface. But since building and maintaining software can be cheaper now it can be better to maintain a 1-5k LOC vibe coded version that meets your security bar than to trust an external party's governance & quality. This has the additional benefit of reconsidering if you even need the dep or if you can reuse something you already have (since you may not want to maintain the lib).

In new software I write these days I limit the number of external dependencies and mostly vibe code anything I need besides the most critical foundational libraries (increasingly I am replacing these as well).

I think this, the supply chain attacks and binary reverse engineering will cause us to go back to thin clients, html over the wire and vibe coded libs instead of external open source deps.

Basically everyone has a sandbox of some sort to run agents inside. Everyone has a registry of some sort for tools. Everyone has a way of running agents inside a sandbox and giving it some tools.

Now the stuff people are coming up with is: how do you do authorization in this model? do you need a full sandbox all the time or can it be a workflow? how do you specify an agent is it a prompt or does it have some kind of control flow structure? How do you coordinate among many running agents?

I would say thats where we are now is there’s loads of people all solving the same problems a bit like when CoreOS, Kube etc. were all competing.

I think I missed why is this faster? What I’m reading here is it’s similar to constrained decoding but I’m not seeing the explanation of why it’s able to get those results.

This thread should be on the first page of every book on microservices.

My take on this is they are a tool to help speed up your work they are not meant to produce finished work. Humans produce finished work. LLM will never be deterministic cause their entire value is that they are generalizable.

This or you just repeat the initial prompt every 200k tokens

I think Elder Scrolls Oblivion was like 80 person core team and 4 years of development and New Vegas was like 70 person dev team and 2 years of development.

But starfield, which was widely criticized by fans, was over 100 people and 8 years development. With the most common criticism from former devs being about the additional management structure and difficulty of communication.

I can’t help but feel there is a lesson there for tech companies where engineering orgs for products are 200+ people when a 20-30 person startup is your top competitor in the vertical.

My favorite is 20th Century Food Court in Last Call BBS. Some of the other games remind me too much of work (I’ve bought all of them including the coincidence card games but I have only beaten this one), whereas this one reminds me of fun times I had making synths in Logic and VCV Rack for fun. Highly recommend!

I always wished they would make a management or simulation game, I think 90% of all programmers play Paradox games or Tycoon games etc. and I know their take on it would be amazing.

Not really if it takes you 15 minutes to write a 50 line function but it takes the AI 90 seconds then you already are at a 10x speedup just for this task.

This (non-yolo mode AI coding) is actually how we used to code in the old days (2023).

As someone who has used multiple vibe coded internal tools: you will care when you use these tools and encounter strange bugs and missing features.

The human touch is visible in the way your features work just like in vibe coded art and games it lacks intention.

Scale to zero is very useful.

When people say “you’re holding it wrong” it tells me they can’t even conceive of a better way of doing it.

The models produce the same slop for everybody, you don’t have a special way of doing it you lack taste and an opinion on your problem domain from lack of research and studying prior work.