Feel free to be a dick to someone else.

This might lead to more automatisation and not less if it works. After all we might extract everything critical to us.

We also now expect juniors to review the other ones code first.

I don't think they are totally usesless.

And its clear that progression is happening on a communith level on all of these and they get integrated later on in commercial offerings like from Anthropic and co.

But also doing a opensource harness and not just giing in to the big companies allows us to have all of this open and transparent and with open models locally.

An expert in physics still needs to write code in python to do their math and analysis. Its an intelligence issue. That person needs to learn a tool.

In medicin you have the modern labs which automate a lot and you have the old labs. These 'neolabs' are better because of intelligence.

A doctor doing a diagnosis can say 'no clue' or can give you a proper answer. The more intelligent this person is, the better the answer.

Might be an architecture issue or a parameter size issue that it didn't learn to do math like a caculator.

But look at your own math skills: How many numbers / how big of numbers can you keep in your head? How far is this heuristic away from how much a human learned until you start using pen and paper or a caculator?

Might break the caching, perhaps this can be solved with snapshot ids or cache ids like "Replacing context line 434-500 with hint; checking last request before that context even was added and running that cache before"

Reinforcement learning can just solve things even if they are new. It doesn't understand how a tool works? Give it a vm with the tool, a thousand agents and let it discover it automatically.

Use the thumbs up/down emoji + chat analysis when a customer is unhappy, feed that to a RL Loop.

The AI Researchers though work on World Models, grounding the AI and letting it simulate. It can do the simulation in parallel (unlimited) and choose what is best.

> I think you miss how much tacit knowledge and judgement there is inside the brains of each of us that an LLM is not capable of.

But thats my problem. Soooo many do not have this even as senior developers.

> Now you have a bug. You do not know even where to start. Thisis theprice to payfor speed, as usual: technical debt.

Yeah now i just ask the LLM to describe to me the bug. Works very well.

> Now you tell me you put three agents to talk and burn 2000 usd in tokens. Great! Is the final solution better than what you would have achieved? Not sure at all.

This is the thing. It only needs to make the team 10-30% better to compensate token budget with one work collegue. We have reached this level in my opinion already. Choosing a head count vs. choosing tokens.

But it becomes cheaper and easier and better. So you will not just be able to do ith with 3 agents but with 20, 50 or 100.

It will be better if your team is an avg team. It will be worse if you have a high profile team, for now. But man our industry has such a weird broad quality spectrum.

> TBH I am not into agents bc I do not trust a tool sniffing all my code and for copyright concerns

In worst case, my team always do code reviews, I do a code review on an ai instead of a human and adjust the harness or the infos the ai can access. I can actually work on making this workflow better and then i can clone it or spin it up for every single PR. For a human? I have to train them and they might leave.

But there are plenty of cases were code doesn't matter. Researchers write a lot of random shitty uggly code as long as it does what it does, it doesn't matter. I have scripts for small tasks, we have microservices which do one thing because it is a tech stack we only need for one use case.

I mean the token prices in general as certain services were never really using a subscription.

I do run a claude subscripton right now though and since there capacity change, i hit the limit rarely in comparision to the past, but I don't think this will stay as it is.

In math its simple: does the verification say its okay.

If its mechanical: is any property better than what we have already.

etc.

I'm pretty sure we will solve this issue. Either already through World Models or another architecture.

It could also be, that we just need a 10 or 100 Trillion Parameter model to match so many generic ways of solving tasks and keeping the concept in the LLMs 'head' to solve it that it will just emerge with parameter size. Like with fable they said that it can chain together exploits which wouldn't work as standalone exploits.

What if the only real barrier is the depth of understanding of concepts and this is exactly what is getting solved with parameter count?

But look how young this field really is if you start counting it when it became relevant on mass. Its not 'just' an LLM which is changing the world, its machine learning overall. Robotics wouldn't be were it is today if its not for machine learning. Took humans time and energy to take the leap, to start learning what the status quo is and then actually doing more with it.

> the paradigm as we know it is a ceiling unless you massively and continuously feed this system with average tasks

While I do think its doable to achieve AGI in 5-15 years, even if it doesn't happen and it always means that people train an LLM or whatever, if you need 10 experts to teach this to an LLM OR every single senior has to teach this to their juniors every single time, the LLM will always win.

I'm now team lead for 10 years and every single year I teach them the same thing over and over and over again.

the craziest thing about this? If i wouldn't tell them what they are doing wrong, they wouldn't even know it.

Quality is already a very flexible term for a lot of people.

> I can agree that for lots of tasks it does not. But for others it is just not a tool good enough.

Yet.

> If you want to ship a sub-par thing that will go to the rubbish in a couple of months, then yes, you can do that. But that will fail commercially any way.

Now we come to the reality: I have seen so much garbage software its crazy. People using md5 as a password hash in 2024! No clue what coding best practices are, teams without code review, teams without a security expert not even knowing what crazy things they do day in day out.

Just a few month ago a team build an API for my team including a Swagger UI. Half of it didn't work. You pressed a button on the Swagger UI and a 500 returned.

And do'nt underestimate what it means that a lot of business people don't like software people. You know that fruit basket we get? and water and stuff? they don't do it because they like us they do it because thats what you have to do. if a Product Owner starts vibe coding with AI, he will have leadership convinved in no time, then it goes on production and it will run for waaaaaay longer than anyone would have guest.

Besides that there is plenty of software were complexity is less relevant or security is not that big of an issue.

We see AI factories going in this direction but there is no real 'the open source ai platform' thingy.

It needs connectors to integrate with k8s, hyperscalers etc. it needs to be able to have a basic router, a way of configuring expert agents and interaction options for the human in the loop.

There is for sure things we need to build or change, but it def feels like to me that it would immediadly fix a few things today.

I'm not disappointed that it doesn't advance as fast as it feels

I don't mind semi-deterministic for plenty of things. But these agents like hermes, can codify a skill to be deterministic.

I would say yes and it will scale. It will either happen through central LLM just paying for it and scaling it up to everyone on the planet (literaly) OR by the agentic layer every big business is building into their systems.

You needed some human to use your tool optimized for their company? With agentic layer you no longer need this. And if you look at companies like Google, they were pushing this notion for ages already because they saw an adoption problem of more 'complex' tools and trying to make it simpler and easier. Now you can act from the other side too.

> We do not have even enough compute power for current technology.

Exactly. Right? There is no ceiling if its clear that we don't even have the hrdware. But the hardware is a bottleneck not a ceiling.

> The ceiling is the paradigm itself, as I mentioned above. There is not a single chance with current technology that something could become "generically knowledgeable" and "reliable" both at the same time.

It doesn't need to be perfect, it only needs to be better than the avg human. And the current LLMs are already better than aat least 1-2 people in my team.

> Now add the human factor of requirements and back and forth

Yeah for now. Grill me skill made it a lot easier. Harness engineering is also being worked on, agentic layer, ai factories etc.

And all of this can be copy and pasted. There is only one harness needed which becomes the expert security reviewer and tomorrow everyone can have it.

I'm still discusing progress with LLMs with people and still not everyone is using it or playing around with harnesses or developgn an agentic layer. We still have a lot of work to do to even see how good it will become while it already is really good.

People are already borred of AI today and making wrong decisions based on the current level of AI while i think we will see continues progress for years.

We are not even close to what AI slowdown looks like.

The whole business side of things are now building Agentic Layer for Business applications. All of this Agentic Layer needs to be build and its happening right now and still needs a little bit of time.

Anthropic and co have the biggest and centralized reinforcement loop on the planet: Millions of people telling them what is good and what not due to thumbs up/down.

And for sure when the businesses are building the agentic layer they might give direct feedback to them.

While in parallel LLMs get better, more generic and a LOT cheaper too.

LLMs are also quite good in writing unit tests and understanding bugs a lot faster than I do, now.

Just a few month back i looked at some yaml stuff for like 20 minutes, played around with it, looked at formatting etc. then i asked the LLM, it immediadly told me what was wrong. I was just blind to that particular wrong char.

Logic bugs? Yeah it can find them too.

Instead of searching some linux issue, i will prompt claude to generate a small analyser script for checking wha tlinux i have, i will tell it what hardware i have and it fixed my issue in like 5 minutes? That would have been a lot longer before.

For me it changes in a way that i would like to have a 24/7 workspace vm setup outside of my work laptop for keeping it running if it wants and looking at it remotely if i want.

The workspace thing would also allow it to have more permissions like downloading, configuring and using headless chrome instead of highjacking my chrome session.

LLMs from Anthropic and co we get through a central tool which buys api tokens from Azure and AWS.

Its surprisingly fast, probably thefastest i have seen technology getting rolled out.

Im more worried about the small/middle sized companies which are software companies but don't get that they are. You know the companies 100% depending on IT but not having the right or good or enough people who often in interviews struggle with basics like code review.

They learn the concept of things and how to do them because this is better compression than learning concepts one by one.

Which means, if an LLM 'learns' the concept of a poem, it can put everything into the formad of a poem instead of learning a billion poems.

Generating a good looking UI for example, is so much easier now with LLM.

For a joke I asked ChatGPT yesterday to make a short promoimage for a 'joke' idea i had, it was above avg. I have for sure seen worse Marketing Images than what ChatGPT generated.

It looked similiar to plenty of other Marketing Images but its not that anyone cares.