The hardest thing in the AI era is the sheer amount of refactoring / deleting of code you have to do to make sure it works well with the latest models.. > spent a month building a knowledge graph only to see a simple folder filesystem with frontmatter and .md files are far far

Humans will delegate all boring things to agents and keep interesting things for themselves.

Software will proliferate just as videos, music, writing did. The market structure will shift from a “fat middle” to mega-aggregators and a long tail. It’ll be a slower process due to network effects, but many traditional vendor lock-ins will get eaten by AI.

Kimi K2.5 continues to be my daily driver for all the basic stuff where I don't need PhD-level intelligence. I just need it done quickly. Running it at 200 tps through Fireworks AI within OpenCode is just such a delight.

Hours of autonomous coding cycles with Grok 4.20. Code generation, trace inspection, edge case patching, loop. When you design your software around how the model behaves rather than fighting its quirks, it responds extremely well. So far it's completed ~30 programming projects,

Models are converging. Context architecture is the moat now. If your agents drift, fix the context — not the prompt.

One of the easiest ways to tell whether the context you gave your agent is actually good enough is to look at the "apology" metric. If your AI agent keeps saying things like "sorry" or "you're absolutely right," that is an indication that the context can be improved. When an

I believe this more than anything right now the most effective startup employees will have custom agents and personal software they bring to their jobs and these people will become 100x employees how I see this working: personally, the way I operate now is simple basically

If your agent misbehaves and writes the wrong code, don’t tell it to fix the code. And don’t fix it yourself. Use that valuable context to figure out WHY it did the wrong thing. Tell it the issue, have it analyze its own context, and have it tell you what docs or skills or

You might think AI engineering is mostly about models. After ~2 years working in this space, I can say it’s far more about software engineering than AI itself. As the OP says, most of the work is around: • event-driven systems • distributed systems • search/retrieval •

An analogy. A software project is like an oddly shaped container that you are trying to fill with water. The shape is the required behavior, and the water is the software. Prompts and plans attempt to define the shape for the AI, but AIs have very poor long term memory, and

Before agentic coders: What doesn't fit into the context size doesn't exist. Agentic coders: What isn't found with grep doesn't exist.

Agentic engineering (vibe coding, but done properly) is just TDD on steroids. Create the loop for the model to test itself, and then let it rip on the features you ask it to build.

Claude code connected to postgres is analytics redefined. I am talking to my data. Literally having a conversation with it!!

AI raises the floor for bad engineers. AI raises the ceiling for solid engineers much much more. The gap is getting wider, not smaller.

ThePrimeagen AIs aren’t good rule followers. The older the rule in the context window, the less priority it is given. So the best way to enforce the rules is with external tools that communicate failure to the AI. Acceptance testers, Linters, dependency checkers, C.R.A.P. analysis. Mutation

One Happy Fellow I think the opposite is likely. With more rapid development comes a greater need to keep the structure under control. This requires more discipline rather than less. The difference with AI is that the medium of craftsmanship will not be code but rather the structure imposed

Kaivalya Apte - The Geek Narrator I disagree. Code is slow for humans. The more we read or write it the slower we go. To gain productivity from AI we need to disengage from code and put our energies into managing the structure, not the syntax, of the code.

AIs are just another step up the semantic expression ladder. We initially expressed our semantics in binary, then assembler, then Fortran, then C, then Java, then Python, etc. AI is just the next step up that same old ladder. And when you take that step, nothing else changes.

Very true. Tools have changed in revolutionary ways; but software engineering has gradually evolved in discipline without revolution. The principles of software design and software architecture remain the same, regardless of era, platform, application, and hardware. And that’s