I am curious how the workflow of people, who do not write code at all, looks like, or what products do they build. In my experience LLMs are an excavator, but you still have to tweak the fine details with a shovel.
I am in the infosec space and do a lot of reading, summarizing of code and a vuln PoC here and there in my day job. Over a busy month I may put out 400-500 LoC.
In my personal life, I am making tools to support hobbies. I typically tackle architecture and design myself and sanity check with an LLM, then Codex does all the programming work.
I'm more interested in making sure the apps I make have the content I want and functionally meets my needs than actually writing the code myself. Making fine detail tweaks are not something I need to do past review and pointing them out to to the LLM.
i agree. just using right now the coding agent to do so, coding, small files, functions, lines of code with mandatory rules and guardrails, scope, and context.
Given that according to some we can code at 10x speed for at least half a year, I wonder where there are some autocoded softwares with 5 years' worth of equivalent human engineering work.
I'll root for DeepSeek v4 Flash as well. It surprised me just how "good enough" it is for most of my needs, and also dirt cheap. Everyone should try it at least once.
fired it up via the $5 opencode go subscription and am stoked. This is an amazing amount of capability for pennies on the dollar. I'm using it alongside my codex and claude max subs. Just fantastic for coding that claude is architecting.
> This is an amazing amount of capability for pennies on the dollar.
True. I doubt how long OpenCode can subsidize $10/mo Go plan for. Its weekly and monthly limits already seem restrictive for some of the most capable models like Qwen 3.7 Max and GLM 5.1. That said, if the tasks are do-able by DeepSeek v4 Pro, Mimo 2.5 Pro, and Qwen 3.7 Plus, then it indeed is a super nice deal. I haven't too many complains other than the fact that these models sometimes require more/detailed instructions than Claude Sonnet / GPT 5.x did.
Don't need much training data for bank/insurance/retail analyst work - it's just basic reasoning and data retrieval. If AI could crack the programming nut - one of the most intellectually challenging professions - it can handle the rest with ease. The only human role will be high level monitoring - and even this will be largely automated so fewer will be required.
> Don't need much training data for bank/insurance/retail analyst work - it's just basic reasoning and data retrieval.
For insurances... there's a reason why the three bullets of the plumber's brother were labelled "delay, deny and depose". You don't need a grunt to compose a denial order. Just let AI default-deny everything, most people won't have the energy left to battle the system or they'll die anyway before the claim finally sees an independent judge.
And as long as insurances aren't severely punished for denying claims that are found out to be valid later on, this dynamic will just continue as-is.
Sorry to reply to myself but I just recalled the recent Apple ad that ran last year about a corporate goofball who got his Apple device to fire off well crafted email slop to his manager who looked surprised/impressed. That trick will only last for a short time. The joke is that people like him and his manager will be the first to be fired.
Given that we can code at 10x speed for at least half a year, one would expect to see at least some pieces of machine-created software with 5 years' worth of equivalent human engineering work.
reply