I'm a coder and a daily driver of ChatGPT and I don't really know what Sol is or how I can access it. I follow discussions here and know of its excistence, but I can't remember its relation to other models or tiers by heart. What ever the default thing the website is giving me has been good enough for my needs for years.
Do you... code by copy pasting chatgpt web???
That's what I do. But I don't write enough code these days to spend time on anything more complicated. For the odd shell script or python program I have ChatGPT write it, then I copy/paste it, make it actually work, and deploy it.
Lots of companies have security policies that forbid installing a local agent/harness. So employees still only have access to the web chat interface, and copy paste content yes.
Yes! Though I mainly use it for one-shotting full files, so I'm not copying over small diffs. I did try copilot at some point in vscode, but after a week or so I felt like it was slowing me down. Something I knew would be a simple and quick change was now slow since I didn't have enough ownership of the code to do it quickly myself, and prompting for the change took longer than changing it manually if I had had full ownership. So I went back to coding by hand things that aren't a one-shot file.
Thanks for the reply. I'd suggest you improve your workflow with better tooling like Codex or Claude code, and if you have some kind of weird constraint they'll easily follow an AGENTS.md with that.
I too use WebUI version, I prefer friction. I have Claude code extension in VScode but I don't use it much except for making small one time projects.
I refuse to pay any money to these companies specifically AND so far I use it solely for things where copy-pasting is entirely fine.
I used free trial of Claude Code and has not seemed to be superior for my usecases.
Just use opencode/pi/etc with an open weight model?
Does it bother you so much to see people out there who can go on without their lives being shaped by the Corporations?
It bothers me when people have terrible inefficient workflows for no good reason
What you think is "terribly Ineffcient" can be also considered "perfectly acceptable and resilient to systemic shocks".
Hyperfixation on efficiency gains is a disease of modern society.
Copy pasting ai code from the browser is not perfectly acceptable. The only reason to do it is because you haven’t tried agents. It shows a lack of imagination and a willingness to settle for inferiority.
I tried Claude in agent mode, as I wrote in grand^4 parent - specifically in https://news.ycombinator.com/item?id=49622329
“Terrible inefficient workflows”, like having to prompt Claude to change one or two words in a file rather than just manually editing it, because it gets confused when the file changes out from under it and will later overwrite the changes?
not familiar with those, will look into how one is using these
That's what I used to do (copy and paste from web ui and with copilot in my code editor).
I started using claude code a couple of months ago and now almost exclusively use it. My workflow is mostly creating a md file describing what I want then telling claude code to look at it and implement it. I simply use the default model 95% of the time.
Just download the ChatGPT app and use the Codex mode.
Using ChatGPT.com for coding tasks has to be a joke in 2026, right? I assumed everyone is using Codex/Claude Code/OpenCode/Pi by now if you’re using these tools.
Yeah! Seems like that's the assumption in this ongoing discussion, so I thought my point of view would be interesting. I'm not saying I'm doing it the right way, possibly I'm being very stupid, but the point here is that it's not just the "normies" who don't know what Sol is.
> it's not just the "normies" who don't know what Sol is.
You are closer to a normie than most here I assume.
No, it's a great point. I think we all live in bubbles and aren't aware of what others around us are doing.
At my admittedly very tiny workplace, I'm the only one who uses agents at all. The rest just use the web interface, though one tried cursor for a bit.
can i have a job there so i can work for like 2 hours a day
Lots of large enterprises and organizations have security policies that make it very hard to self-install these tools and haven’t figured out they should add them to their approved software list yet. Federal government in particular is still very slow
HN vastly over estimate the actual usage of agents, and AI in general. The few times I figure an LLM might help, I just use DuckDuckGos duck.ai.
I use it for making small disposable scripts, and in-browser chat with copy-pasting output works fine for that.
This might depend what you mean by code. In the sysadmin space I ask a web interface for poweshell to generate specific information multiple times a day, and pasting it into a terminal is really the cleanest workflow on a corporate machine where you have to justify running an executable.
There are ways to make copy-paste ChatGPT usable with things like AI Badger. Also, ChatGPT web is unmetered, so you can do review/planning work and only delegate the actual implementation to Codex.
I used to do this until February of this year. Never looked back.
I code by hand (sigh) and copy paste some snippets once in a while from a web chat LLM. This also means every single line of such snippets gets reviewed and anaylzed. Usually, these are some arcane Win32 API usage where otherwise I'd have to dig into old forums. I don't want to become a prompt engineer so I stay away from "agentic" workflows.
You're missing out, for better or worse.
As an engineer, the enjoyment from the process is not less important, or should I say more important, than the enjoyment from shipping a final product.
That's probably the single thing that I found to be biggest difference between those who are very pro AI vs. those more reserved or negative.
A colleague has openly stated that he very much does not care for the process, he just want the product. Where I only care about the product in the sense that I have to, because it's my job and for hobbies I pretty much only care about the process. So an LLM pretty much doesn't make sense, because it help by removing the part I care about. They are good tools for debugging and if you're hopelessly stuck on a detail of some weird and obscure API or configuration.
As an engineer, I know what I'm getting paid to deliver is the work product. I don't have too much attachment to any particular set of tools to get there.
If we follow that logic, I believe it means that you would be quite happy in the Product Owner role, or in the role of a client who outsources the actual development activities. I wouldn't.
Do you think the company that pays your wage thinks the same?
Yes, engineer experience/happiness is part of the equation. The company also thinks that agentic workflow will clutter the codebase.
ah what a throwback.. I thought I was so efficient copy pasting all day long
I call it by it's official name: MCP (Manual Copy-Paste)
MCP when token budget is running low. The web interface is token frugal because it has to work with whatever I provide.
Its mostly used with Codex so you can give finer control over task delegation.
its definitely worth learning the different strengths and weaknesses for each one and which you should use for planning/building/testing/documentation updates etc.
No point in burning excessive tokens using a high tier/expensive reasoning model like Sol/Xhigh if just updating a readme file.