Featured question
Curated by Daniel Griffin ·
What when it comes to AI in software engineering are you struggling with the most?
Armin Ronacher asks; Dillon Mulroy points to the replies as the realities of agentic engineering.
Addendum 01
What the thread kept circling
The replies do not collapse into one complaint. They describe a connected system of pressures—attention, understanding, verification, code quality, teamwork, judgment, and the tools around the work. These six themes bundle the recurring patterns without pretending the boundaries between them are clean.
- Comments shown
- 279
- Posts classified
- 293
Authorship: Codex (GPT-5) authored this addendum for Daniel Griffin. Codex read a random sample to form the initial categories, used Jev to assign one primary label to all 293 collected posts, bundled those labels into the six reader-facing themes, wrote the explainer and definitions, and selected the 12 representative examples. Daniel directed the featured question, source, hat tip, and requested the bundled explanation with definitions and examples. The quoted replies remain the words of their linked authors. X showed 279 comments. Expanding nested branches yielded 293 unique conversation posts. The six themes cover 249 substantive posts. Thirty-nine non-substantive replies and five mixed or outlying replies are not presented as themes.
THEME 01
71
classified posts
Orchestrating without frying your attention
The work shifts from writing code to allocating attention across agents, context windows, workflows, and decisions. The speed can feel exhilarating while flow, sleep, and the ability to slow down become scarce.
“Workflows. How to get agent to follow complex processes and workflows with validators, gates, rollback, dynamic batching or expansion, condition branches, retries, nested loops, etc.”
@rayliverified ↗ (opens in a new tab) “Definitely don’t feel in flow state as much. I think the benefits of it on your brain were kinda underrated until we lost it.”
@twigpress ↗ (opens in a new tab) THEME 02
46
classified posts
Understanding—and still owning—the work
Generation can outrun comprehension. People describe blurry mental models, weak memory of recent changes, and a deeper worry that the craft, agency, or identity they valued is slipping away.
“Cognitive debt is #1, it's too tempting to just ship stuff that you ‘somewhat’ know how it works, regardless of it being buggy or not. A few years ago I had a crystal clear image of the whole systems I work with. Now it's blurry at best.”
@fernandezpablo ↗ (opens in a new tab) “Identity crisis with my direct reports. ‘I'm a programer that's my craft—I no longer program just proompt.’”
@martinheisenbe1 ↗ (opens in a new tab) THEME 03
46
classified posts
Trusting and reviewing the change
Verification and review become the same bottleneck at different scales. Engineers need confidence in tiny edge cases and change boundaries while code, diffs, and parallel tasks arrive faster than humans or CI can inspect them.
“verification. important tiny edge cases. benchmarks are easy but tiny sharp edges make product feel like slop”
@pgray__ ↗ (opens in a new tab) “Code reviews. I'm not prepared for the volume of code LLMs are producing. By me, by my teammates, by automated agents within our product boundaries. I don't know the answer for it, but code reviews must go through a complete paradigm change.”
@bpaulino0 ↗ (opens in a new tab) THEME 04
27
classified posts
Keeping the codebase coherent
Fast generation makes structural drift cheap: duplication, overengineering, oversized abstractions, and locally plausible code that leaves the whole system harder to maintain.
“I struggle to keep the code base clean as a built a product iteratively. When I reach v1.0, I usually do a full rewrite based on a detailed spec on what it turned out to be. That usually shrinks the code by 40–70%.”
@gopietz ↗ (opens in a new tab) “constantly fighting the drift away from quality software.”
@onarchbtw ↗ (opens in a new tab) THEME 05
30
classified posts
Working together—and choosing what to build
Teams have not settled on shared norms for AI use, collaboration, responsibility, or quality. At the same time, greater implementation capacity raises the value of product judgment: deciding what deserves to exist and preventing unrequested scope.
“What collaboration with peers look like. Things like ‘pair programming’ don’t seem to make sense anymore. But it’s important for knowledge sharing and team bonding to do things together, but I don’t know exactly what these ‘things’ are atm.”
@oxfernando ↗ (opens in a new tab) “figuring out what to actually build with it”
@flandermaxx ↗ (opens in a new tab) THEME 06
29
classified posts
Making the tools fit the work
The surrounding interface matters: verbosity, blocked conversations, poor explanations, token costs, hardware limits, privacy rules, and security restrictions all shape whether agentic work is usable.
“I find it annoying that I need to constantly beg agents to: 1. explain why they did something (i.e what they've learned about the code) 2. to explain it in fewer words :) Also: I really dislike agents blocking the convo thread to compile code/do work. They should offload more.”
@davidjustodavid ↗ (opens in a new tab) “Artificially inflated hardware costs; privacy; cyber limitations deciding how I am allowed to use the frontier models.”
@syndrowm ↗ (opens in a new tab)