I built a tool specifically for dealing with remote mcp servers via the cli. No config files needed. FUSE (and Bash) is all we need. This way we can still get benefits of discoverability of mcp endpoints, but can use cli tools and bash to do things easier.

https://github.com/turlockmike/murl

When producing code is cheap, you can spend more time on verification testing.

Force the LLM to follow a workflow, have it do TDD, use task lists, have it write implementation plans.

LLMs are great coders, but subpar developers, help them be a good developer and you will see massive returns.

Coz I have always done coding this way with humans I started out using LLMs to do simple bits of refactoring where tests could be used to validate that the output still worked.

I did not get the impression from this that LLMs were great coders. They would frequently miss stuff, make mistakes and often just ignore the instructions i gave them.

Sometimes they would get it right but not enough. The agentic coding loop still slowed me down overall. Perhaps if i were more junior it would have been a net boost.

I believe in a very practical definition of AGI. AGI is a system capable of RSI. Why? Because it mimics humans. We have some behaviours that are given to us from birth, but the real power of humans is our ability to learn and improve ourselves and the environment around us.

A system capable of self improvement will be sufficient for AGI imo.

Ah - recursive self improvement. I was thinking repetitive strain injury was odd. But that's probably quite a good test although LLMs may be able to improve a bit but still not be very good. An interesting point for me is if all humans went away could the AI/robots keep on without us which would require them to be able to maintain and build power plants, chip fabs and the like. A way to go on that one.

Self improvement doesn’t mean self improvement in any possible direction without any tradeoffs. Genetic algorithms can do everything an LLM can given enough computational resources and training, but being wildly inefficient humanity can’t actually use them to make a chatbot on any even vaguely relevant timeline.

MCP is just JSON rpc with one useful command (list-tools). Turns out that's probably all we ever needed.

WSDL has entered the chat

This boils down to a fundamental question. Why do we spend any time doing science to begin with? Historically scientists were drawn to the field in order to improve human understanding of our reality. These individuals often died quite poor and unknown, but advanced us forward. Now popular science is the goal and getting huge money grants. The goal is no longer the pursuit of knowledge, it's a money game. Like journalism. The only useful science done at the moment is at tech companies who will use it to build better products.

> The goal is no longer the pursuit of knowledge, it's a money game.

I don't know about that. All the PhDs I know are dirt-poor (or were until they left science to get tech jobs), and are in the game because they are passionate about science and the project of advancing human knowledge.

It's true that your ability to get a tenure-track position is very dependent on your ability to successfully obtain grant money, but most of the scientists I know view that as a necessary evil, not the game in itself.

> The only useful science done at the moment is at tech companies who will use it to build better products.

This is trivially demonstrably false. https://en.wikipedia.org/wiki/James_Webb_Space_Telescope for the first example that came to mind from recent news.

I definitely exaggerated, but a great example of the opposite case is CERN. Physicists knew the limits of what could and couldn't be tested with it, but they hyped it up to convince governments to spend money anyway. The JWST is a much more fruitful project, but how many of those are there compared to projects that just focus on getting grant money. We should build more telescopes and fewer participle accelerators, but the grant money doesn't match the need since it's hard for politicians to understand.

It is true in the field of computer science at least where the market has destroyed the academic sphere in terms of innovation by building better products.

As a small software vendor, this doens't seem accurate to me. My whole field is reading the papers but very often the scientists are ahead. It's their job to discover new territory, while we also have to deal with more mundane "product" tasks. Industry will do the "fine-tuning" but not really the innovation, or just small innovations. So from a consumer point of view, it might seem that industry people are ahead with their product output, but the new science is light-years ahead of that.

Diego Ongaro wrote the Raft paper as his PhD dissertation at Stanford, so this is also false.

I’m sure the original claim can be narrowed even further than you just did to make it true; I don’t deny that there is a trend for more research, particularly CS and biotech, to be done privately. It’s hyperbole to claim academia is doing nothing though, even in CS.

Pretty sure the money a scientist can personally earn with grants is far less than they can at a tech company.

This is absolutely true.

I could leave for industry tomorrow and likely double my salary.

The money I've personally earned from grants is... $0. And I've been very successful in getting grants.

I only got a job offer at one university where the PI of a grant directly got a monetary benefit from it, and while it was nice, it was never going to be more than "That's a nice little bonus" money.

If you want to make money as a scientist in academia, consulting or a startup is where it's at.

> Historically scientists were drawn to the field in order to improve human understanding of our reality.

I doubt that in the general case. People have always been driven by base selfish motives.

True, but such selfish motives can be generic (e.g. personal glory) - and if directed into scientific endeavours can still result in genuinely passionate enquiry.