No. You can absolutely build things with AI small or large and understand it. If you don’t understand it. Then you’re not caring about the output to begin with and not guiding it to build the solution you want.
The word "understand" seems to mean something different to you.
If I understand something, I could write it in assembly if I wanted to. It might take a long time, but I know every level of the stack under my code down to bare metal.
Maybe an AI level of "understand" i.e the same understanding a Senior has of a Junior's code based on daily check-ins is enough for 95% of "boring" programming. But for some tasks you need to either fully understand the code or just tolerate bugs.
At the level of complexity I work at, it's (often) faster to just code it myself than to expect AI to converge on a result I like and then hand check it.
> At the level of complexity I work at, it's (often) faster to just code it myself than to expect AI to converge on a result I like and then hand check it.
Would love an example because no one has ever been able to give a coding example that AI isn’t helpful for. I had one person on linked in try claim their undocumented audio hardware won’t work with ai but when we got ai to probe it and build docs it ended up solving a bunch of complex bugs they couldn’t fix.
Impressive, also horrifying. I love what I do and if AI can do it better than that sucks.
Anyway the use case for me is to realize a new visual style through graphics programming. It's a lot less measurable for an interative AI agent than "Meet this hardware specification from a device with a discoverable API"
I have no doubt AI could create a LOT of variations on "a new visual style" but it's less controllable than just doing it yourself.
Btw, did you "understand" the sound driver after the AI coded it? Could you modify it without further help?
Right now, at least, I haven't found an AI capable of replacing a software engineer. Ive seen AI that can easily replace basic programmers, however.
I also think AI can replace non-coding artitects, and probably most middle management type jobs (my company has 6 levels of management between the CEO and "individual contributors" in my area (8 counting inclusivity)).
That's a lot of management levels, and every level has to be paid more than the level they manage as a fraud disincentive. So that's a lot of money...
Can you explain the fraud disincentive bit? I feel like there's something obvious I'm missing, but why would a manager earning less than their reports make fraud more likely?
Look, goals can differ. If you don't need to understand and predict every part of the code the AI is generating and you just need it to meet a "sketch" of what you want - by all means use AI. I do use AI in that situation for related or unimportant code.
But if you need full understanding, in my experience the only way to get that is to program it yourself. Unless what the AI is generating is so trivial you already understand it and it's grunt work, you will learn the detail by doing it yourself. Controlling the approach here is important.
However often the best way to handle grunt work is to write better abstractions, something AI sucks at.
It's the programming equivalent of many PG essays. https://www.paulgraham.com/useful.html for instance. There was one on how PG refined their thoughts via writing. It's in there somewhere.
As someone who spends way too much time searching for the best abstractions, absolutely this is still true.
I often have a long back and forth with codex to explore the problem space and settle on the best abstractions. Occasionally it will make a suggestion that helps me, but for the most part it's reviewing while I'm in the driver's seat.
Contrast this to simply giving it a function name and a vague description of what the function will do. I'll generally accept its output with a few refinements.
But for larger project structure and metaphors, it falls flat, and often lands on a solution that's going to be a maintenance nightmare or result in endless repetition across not-quite-the-same cases. I've never seen it happen upon an appropriate abstraction that can cleanly cut through the nonsense.
People seem to ignore the fact that with MCP you can serve up the tools the user wants and has access to instead of a rest api doc specifying every endpoint and bloating the context.
All those tools still get into context. Also, it's not hard to filter a rest api doc - like with a special tool for that the harness itself could pre-filter it and add only the relevant ones as tools to be even more leaner than what an MCP returns.
100% up to the harness. Most harnesses either fixed (or dymanically depending on size) nowadays add a "search_tool" tool to prevent spamming the context with all tools.
I don’t like it. Structures responses really do not work well with LLMs at all. They are one of the biggest causes of issues with tool calling right now.
Agree with sibling. If you're getting severely deteriorated results with structured output, you're probably doing something wrong. There's been some research on the impact of structured outputs on results distribution, and there are tradeoffs, but "do not work well at all" doesn't match the experience at large.
You prefer having the harness execute any markdown that looks like it might be a tool call? I had a bad time getting that to work reliably whereas a grammar in the sampler gets it right every time.
So were Microsoft employees until they got forced to use copilot. Everyone seems to think MS got rid of Claude Code due to cost but it had nothing to do with cost. Employees weren’t even using copilot. Can’t make a product better if you don’t use it. Meta should be the same. Use your own product.
Idk why they wouldn’t use it. It’s fine, and it’s good that you get all the models rather than locking yourself into Claude models when GPT-5.6 exists. Claude Code did have a big advantage early on before GH Copilot got agent mode though.
You don't need to "justify" Zig's existence. It exists, and people like it, and that's enough. IMHO, I wouldn't use it, but there are valid use cases, even if it's "just" a nicer C.
I think there's no denying they each have an ideological bent (as is their right as private companies). I have had Copilot deny me access to historical information on ethical grounds, even though I don't think anyone would find it controversial (clearly it was overtuned, GPT and Claude had no problem answering the same question). What is different though is that they are each allowed to have their own perspective instead of a singular mandated one.
That was guard rails in the harness. Not the model. We are talking about baking it into the model. Denying to do something is also very different to changing historical facts like China does.
> very different to changing historical facts like China does.
Oh but they're trying. The right-wing usage of things like "woke" and "DEI" primarily serve to hide/destroy historical realities. [1]
Florida has it's "STOP WOKE" act that forces teachers to talk about how slaves learned skills/benefited from slavery[2] and that various massacres also had black perpetrators.
What is this other than changing historical facts? About fucking chattel slavery for Christ's sake.
And also, not taking a side here, plenty of woke partisans valued righteousness over truth in the 2020 era. The 1619 project which was a whole NYT backed big thing had a bunch of factual errors.
The real rub is when you get into "shared facts" that Americans were all taught in high school civics but the rest of the world wasn't. If you've mostly been in America, it can seem like someone's deliberately lying about history but they simply weren't properly educated with the Correct Interpretation.
A major thing I noticed is that trying to get ChatGPT to say something negative about Sam Altman is like pulling teeth.
Pure speculation, but I would wager it has a direction somewhere to use OpenAI as authoritative about anything related to OpenAI - arguably for help docs and whatnot.
So you went from a bad product to a worse product? There’s good solutions out there and you’re like “nope don’t want a good solution. I want a worse solution.”
^ this is literally what the op did. Don’t flag facts.
reply