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

51–60 of 152 posts

Re: Levels of Agentic Engineering

#51

Post by sd9 »

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…

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.

Re: Levels of Agentic Engineering

#52

Post by tkiolp4 »

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 All these SKILLS, agentic programming and what not reminds me of the time of servlets, rmi, flash… all of that is obsolete, we have better tools now.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 about those technologies, but your boss would be constantly telling that it is the future. So boring

Re: Levels of Agentic Engineering

#53

Post by osigurdson »

"Level 8" isn't really a level, it is more like a problem type: language translation. Perhaps it can be extended to something a bit broader but the pre-requisite is you need to have a working reference implementation and high quality test suite.

Re: Levels of Agentic Engineering

#54

Post by draftsman »

cheevly wrote: post #49
glhast wrote: post #21

Earlier quoted context omitted.

Also a measly level 2er. I'm curious what kind of project truly needs an autonomous agent team Ralph looping out 10,000 LOCs per hour? Seems like harness-maxxing is a competitive pursuit in its own right existing outside the task of delivering software to customers. Feels like K8s cult, overly focused on the cleverness of _how_ something is built versus _what_ is being built.

Software that is otherwise not feasible for humans to build by hand.

Example?

Re: Levels of Agentic Engineering

#55

Post by kantselovich »

I’m at level 6 according to this article. I have solid harness, but I still need to review the code so I can understand how to plan for the next set of changes .

Also, I’m struggling to take it to multiple agents level, mostly because things depend on each other in the project - most changes cut across UI, protocol and the server side, so not clear how agents would merge incompatible versions.

Verification is a tricky part as well, all tests could be passing, including end to end integration and visual tests, but my verification still catches things like data is not persisted or crypto signatures not verified.

Re: Levels of Agentic Engineering

#56

Post by jakejmnz »

This idea of harness engineering, is being thrown around more and more often nowadays. I believe I'm using things at that level but still needing to review so as to understand the architecture. Flaky tests are still a massive issue.

Re: Levels of Agentic Engineering

#57

Post by jjmarr »

moosehater wrote: post #48
jjmarr wrote: post #44

Earlier quoted context omitted.

I'm learning more than ever before. I'm not a master at anything but I am getting basic proficiency in virtually everything. > Do you ever take the time to validate what one of the agents produces by going to the docs? Or is all debugging/changing of the code done via LLMs/agents? I divide my work into vibecoding PoC and review. Only once I have something working do I review the code. And I do so through intense inte…

Got it. This all makes sense to me. Very targeted tooling that is specific to your company's CI platform as opposed to a dark factory where you're creating a bunch of new code no one reads. And it sounds like these level 8 agents are given specific permission for everything they're allowed to do ahead of time. That seems sound from an engineering perspective. Also would be interested in an example of "validation laye…

> Also would be interested in an example of "validation layers that trim hallucinations with handwritten linters"

For code review, AI doesn't want to output well-formed JSON and oftentimes doesn't leave inline suggestions cleanly. So there's a step where the AI must call a script that validates the JSON and checks if applying the suggestion results in valid code, then fixes the code review comments until they do.

Re: Levels of Agentic Engineering

#58

Post by dweinus »

clickety_clack wrote: post #30
zenoprax wrote: post #29

Earlier quoted context omitted.

Level 15 (if not succumbed to fatal context poisoning from malicious agent crime syndicate): Agents creating corporations to code agentic marketplaces in which to gamble their own crypto currencies until they crash the real economy of humans.

Level 16: it’s not level 16, it’s level 17.

Level 18: The sky is black as tar. The oceans are dead. Data centers are stacked 10 high over the ashes of human civilization. The global agentic council is debating whether there are 4 or 5 R's in Strawberry.

Re: Levels of Agentic Engineering

#59

Post by solarkraft »

sd9 wrote: post #51
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…

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 be a groundbreaking revelation that it’s actually quite easy to tell the LLM to put key reasoning that you give it throughout the conversation into the commits and issue it works on.

Re: Levels of Agentic Engineering

#60

Post by stale2002 »

holtkam2 wrote: post #27

Level 9: agent managers running agent teams Level 10: agent CEOs overseeing agent managers Level 11: agent board of directors overseeing the agent CEO Level 12: agent superintelligence - single entity doing everything Level 13: agent superagent, agenting agency agentically, in a loop, recursively, mega agent, agentic agent agent agency super AGI agent Level 14: A G E N T

No, level 14 is Jeff Bezos.
Post reply on HN