We could cause the same change with reasonable public transit. Maybe driverless trucks but I think we're a long ways from that still, people aren't going to accept a tanker of gasoline flying down the highway with nobody driving it
No. But most software products are nowhere near that sensitive and very few of them are developed with the level of caution and rigor appropriate for a safety-critical component.
What works: delegating non ambiguous tasks, let them happen in async, while supported by harness of preexisting automated tests, and established project conventions
What does NOT work: I have no idea how to do sth, and I hope agentic coding will solve my problem.
Think "Eisenhower matrix":
- X: Ambigous <-> Trivial
- Y: Can wait <-> Urgent
Urgent&Ambigous => Agentic Coding is useless, and an act of desperation
Can wait and at least non amibogus => Agentic Coding is perfect fit
Think chefs at top restaurants for example: washing hands is something obvious, no need to get any customer infected with fecal bacteria in order to convince the restaurant management for investing into soap (hygiene takes time, you could serve additional customer!)
It is one of career progression milestones for a programmer when they can set a bar for their craftsmanship themselves. Successful SWE is someone who got hired at a team which does not require this kind of education. A team where this type of engineering hygiene is obvious like breathing.
Im actually curious what happens in a professional kitchen when someone isnt pulling weight on menial tasks like scrubbing or batch prep. I know what usually happens in software teams - nothing
Having worked in professional kitchens, my experience is that nothing predictable happens.
It depends not just on management, but also on the personal relationship between management and the person, and on how bad the current market for staff is.
That said, the kitchens I've worked in were filled with people who worked as hard, or harder than the FAANG teams I was a part of.
If someone is giving life-coach type advice, an ad hominem actually might be relevant, right? The blog post doesn’t really make any arguments, it is just advice based on his observations. Which is fine, but it hinges on his expertise.
An ad hominem isn't always a fallacy. If you put yourself out as someone with credibility or expertise in a field and use that to back up your ideas, you have put your credibility on the table to attack.
"Workflow" is the aspect we should try to eliminate, and a LLM+VM combo allows you to do that.
Workflow means you provide tools to the LLM, and ask to make use of them to achieve the goal. This works well already, but it fails whenever an unusual problem appears that is not covered by your predefined set of tools.
Another issue is that the workflow based approach is always linear even if it is a DAG, or even if you have some kind of loop.
The next step is to not provide any tools to the LLM, and ask it to invent them on-the-fly. Some problems need to be brute-forced.
Just thinking opposite direction: if you were to spawn a new planet with life somewhere in the universe, how would you do that? Micro manage every detail, or rather prepare proper conditions, and see what happens?
Wouldn't the "proper conditions" eventually look like series of coincidences?
For many years we were fine with running DLLs, Java .class deps, npm modules, brew packages etc. why do you think we need so much isolation for left-pad class mcp tools?
reply