Who is american…

I’m aware, and I wish people were more clear about the difference, but its LLMs that are driving these insane buildouts, not the other disciplines. This article is clearly talking about the LLM “AI”, not bioinformatics or anything that may actually be fruitful.

The LLM companies like to claim they’ll solve cancer, but its all snake oil hedged on a mythical AGI popping up and fixing everything.

Medical imaging and medication development would be bespoke models no? Not standard LLMs?

LLMs aren’t gonna give us any of those things. Thats just snake oil.

I get that analogy. However, I would heirarchaically place the agents as subordinates to the developer, which is why I would expect each developer to institute their own customised agents.md file, rather than it being dictated from the repo, which is a level removed.

but agents do

Depends on the model, Gemma 4 is extremely lazy in my experience, half the time it won’t finish the task properly anyway. Deepseek (not sure of the version) was crazily overactive. I personally prefer Gemma’s laziness, because it avoid making the chaotic changes that need to be rolled back, but thats a personal preference.

And thats kinda why I don’t like it being committed. If the entire team is using one model, then sure, commit the agents.md, and everyone gets a sane default, but given this is a multi-developer project with likely many different agents and models in use, it makes more sense to me that each developer manages the agents.md themselves and optimises it for their own model/workflow.

At least for the specific example given, I want developers to do the commit part themselves, so if their LLM is doing any part of that, its already a mistake IMO.

I had a very quick look at the AI agent guidelines, and nothing about them strikes me as overly burdensome for a human to fix up. So I’d rather just do that myself (if I were a kernel dev).

My main objection is forcing it on developers, it should be up to each dev to configure and manage their own agent. Making it a suggestion is fine, just don’t commit it. Also, if developers are using local hosted models, then context may be quite limited, so wasting it on an Agents.MD maybe be unideal.

I’m on board with committing formatter config, because thats deterministic and really should be shared amongst a team.

I don’t get why the agent needs to have the contrib guidelines, it should be a human doing the actual contrib part, so its just a waste of tokens for the LLM to read it?

I don’t get why agents.MD needs to be committed. It feels a bit like committing IDE settings, everyone is going to have slightly different preferences, so its better to just have everyone do their own thing. If anything, I prefer to .gitignore itso it doesnt get accidentally committed.

It is a good idea. Firmware updates can improve stability and performance. Just because it failed this time doesnt mean that all the other times it silently worked were also bad ideas.

I think its simpler than that, its just stock price pumping. They can tell the plebs that they have the tech to put servers in space, and the plebs will eat it up and pump the stock.

You can still destroy the terrestrial base stations.

Casual users don’t need to setup vlans, because they simply don’t care.

There is no point hand-wringing about this, they don’t care, they don’t need our help for this.

You say its random, but its actually my banking password.