Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Levels of Agentic Engineering

bassimeledath.com

Post reply on HN
Print view View original

61–70 of 152 posts

Re: Levels of Agentic Engineering

#61

Post by hansonkd »

tkiolp4 wrote: post #52

I want to move on to the next phase of AI programming. All these SKILLS, agentic programming and what not reminds me of the time of servlets, rmi, flash… all of that is obsolete, we have better tools now. Hope we can soon reach the “json over http” version of AI: simple but powerful. Like imagine if you could go back in time and servlets and applets are the big new thing. You wouldn’t like to spend your time learning…

skills obviously are a temporary thing. same with teams. the models will just train on all published skills and ai teams are more or less context engineering. all of it can be replaced by a better model

Re: Levels of Agentic Engineering

#62

Post by svstoyanovv »

solarkraft wrote: post #59
sd9 wrote: post #51

Earlier quoted context omitted.

I had a hunch that this comment was LLM-generated, and the last paragraph confirmed it. Kudos for managing to get so many upvotes though. "Where most [X] [Y]" is an up and coming LLM trope, which seems to have surfaced fairly recently. I have no idea why, considering most claims of that form are based on no data whatsoever.

It’s still an insightful and well written comment, but the LLM-ness does make me wonder whether this part was actually human-intended or just LLM filler: > The discipline to do it consistently enough that agents can actually retrieve and use it is what's missing, and structuring it for that purpose is genuinely underexplored territory Because I somewhat agree that discipline may be missing, but I don’t believe it to…

Suppose you spend months deeply researching a niche topic. You make your own discoveries, structure your own insights, and feed all of this tightly curated, highly specific context into an LLM. You essentially build a custom knowledge base and train the model on your exact mental framework.

Is this fundamentally different from using a ghostwriter, an editor, or a highly advanced compiler? If I am doing the heavy lifting of context engineering and knowledge discovery, it feels restrictive to say I shouldn't utilize an LLM to structure the final output. Yet, the internet still largely views any AI-generated text as inherently "un-human" or low-effort.

Re: Levels of Agentic Engineering

#63

Post by taude »

efsavage wrote: post #4

Yegge's list resonated a little more closely with my progression to a clumsy L8. I think eventually 4-8 will be collapsed behind a more capable layer that can handle this stuff on its own, maybe I tinker with MCP settings and granular control to minmax the process, but for the most part I shouldn't have to worry about it any more than I worry about how many threads my compiler is using.

Agreed a bit. I'm probably too paranoid for MCP, but also don't mind rolling my own CLI tools that do the exact minimum I need them to do. Will see where we're at in a year or so....

Re: Levels of Agentic Engineering

#64

Post by sd9 »

svstoyanovv wrote: post #62
solarkraft wrote: post #59

Earlier quoted context omitted.

It’s still an insightful and well written comment, but the LLM-ness does make me wonder whether this part was actually human-intended or just LLM filler: > The discipline to do it consistently enough that agents can actually retrieve and use it is what's missing, and structuring it for that purpose is genuinely underexplored territory Because I somewhat agree that discipline may be missing, but I don’t believe it to…

Suppose you spend months deeply researching a niche topic. You make your own discoveries, structure your own insights, and feed all of this tightly curated, highly specific context into an LLM. You essentially build a custom knowledge base and train the model on your exact mental framework. Is this fundamentally different from using a ghostwriter, an editor, or a highly advanced compiler? If I am doing the heavy lift…

The problem is: the structure of LLM outputs generally make everything sound profound. It’s very hard to understand quickly whether a comment has actual signal or it’s just well written bullshit.

And because the cost of generating the comments is so low, there’s no longer an implicit stamp of approval from the author. It used to be the case that you could kind of engage with a comment in good faith, because you knew somebody had spent effort creating it so they must believe it’s worth time. Even on a semi-anonymous forum like HN, that used to be a reliable signal.

So a lot of the old heuristics just don’t work on LLM-generated comments, and in my experience 99% of them turn out to be worthless. So the new heuristic is to avoid them and point them out to help others avoid them.

I would much rather just read the prompt.

Re: Levels of Agentic Engineering

#65

Post by blackcatsec »

sd9 wrote: post #64
svstoyanovv wrote: post #62

Earlier quoted context omitted.

Suppose you spend months deeply researching a niche topic. You make your own discoveries, structure your own insights, and feed all of this tightly curated, highly specific context into an LLM. You essentially build a custom knowledge base and train the model on your exact mental framework. Is this fundamentally different from using a ghostwriter, an editor, or a highly advanced compiler? If I am doing the heavy lift…

The problem is: the structure of LLM outputs generally make everything sound profound. It’s very hard to understand quickly whether a comment has actual signal or it’s just well written bullshit. And because the cost of generating the comments is so low, there’s no longer an implicit stamp of approval from the author. It used to be the case that you could kind of engage with a comment in good faith, because you knew…

I hadn't considered this so eloquently with LLM text output, but you're right. "LLMs make everything sound profound" and "well-written bullshit".

This has severe ramifications for internet communications in general on forums like HN and others, where it seems LLM-written comments are sneaking in pretty much everywhere.

It's also very, very dangerous :/ Because the structure of the writing falsely implies authority and trust where there shouldn't be, or where it's not applicable.

Re: Levels of Agentic Engineering

#66

Post by captainkrtek »

There seems to be so much value in planning, but in my organization, there is no artifact of the plan aside from the code produced and whatever PR description of the change summary exists. It makes it incredibly difficult to assess the change in isolation of its' plan/process.

The idea that Claude/Cursor are the new high level programming language for us to work in introduces the problem that we're not actually committing code in this "natural language", we're committing the "compiled" output of our prompting. Which leaves us reviewing the "compiled code" without seeing the inputs (eg: the plan, prompt history, rules, etc.)

Re: Levels of Agentic Engineering

#68

Post by braebo »

captainkrtek wrote: post #66

There seems to be so much value in planning, but in my organization, there is no artifact of the plan aside from the code produced and whatever PR description of the change summary exists. It makes it incredibly difficult to assess the change in isolation of its' plan/process. The idea that Claude/Cursor are the new high level programming language for us to work in introduces the problem that we're not actually commi…

If branches are tied to linear ids then gh cli and linear mcp is enough for any model to get most of the why context from any commit

Re: Levels of Agentic Engineering

#69

Post by braebo »

hansonkd wrote: post #61
tkiolp4 wrote: post #52

I want to move on to the next phase of AI programming. All these SKILLS, agentic programming and what not reminds me of the time of servlets, rmi, flash… all of that is obsolete, we have better tools now. Hope we can soon reach the “json over http” version of AI: simple but powerful. Like imagine if you could go back in time and servlets and applets are the big new thing. You wouldn’t like to spend your time learning…

skills obviously are a temporary thing. same with teams. the models will just train on all published skills and ai teams are more or less context engineering. all of it can be replaced by a better model

My use of skills is more like prompt templates for steering as opposed to the traditional sense of the word skill

Re: Levels of Agentic Engineering

#70

Post by hkonte »

vidimitrov wrote: post #26

Level 4 is where I see the most interesting design decisions get made, and also where most practitioners take a shortcut that compounds badly later. When the author talks about "codifying" lessons, the instinct for most people is to update the rules file. That works fine for conventions - naming patterns, library preferences, relatively stable stuff. But there's a different category of knowledge that rules files hand…

[dead]
Post reply on HN