One question. Sonnet for tool use? I am just guessing here that you may have a lot of MCPs to call and for that Sonnet is more reliable. How many MCPs are you running and what kinds?
Nice article. I saw someone depicting the future of web search with AI. The conclusion was not the bright future. Simply put, ads will never go away. Either AI providers will get paid for whitelisting ads, or even worse these AI will directly promote advertised products.
People could collectively decide to start paying for stuff and most of our gripes could at least switch to providers not accommodating their customers.
To which I'd say to the advertiser, "Good luck paying off the AI adblocker running in my closet at home."
Then again, let's not be too hasty here. Let's see what you're willing to offer. I can sell you the eyeballs of the AI ad-watcher running in my closet for $10/impression. Or, for $1000/impression, you can bring your message to the attention of myself, an actual human. A bargain at any price!
I like the analogy to woodwork and hammer. It fits perfectly to what happens when they do not pay enough attention to the end result. They are not showing the actual product because it is not as shiny as their new agentic hammer.
It matters to me. Claude code is more extensible. They put a lot of efforts to hooks and plugins. Codex may get the job done today. But Claude will evolve faster.
None of that matters if the model is worse. I say this as someone who uses both Claude Code and Codex all day every day — I agree with others in this thread that CC has much better UX and evolves faster, but I still use Codex more often because it's simply the better coder. Everything else is a distant second to model quality.
What kind of tasks are you having success with on codex? I’ve had the opposite experience. I’ll occasional compare solutions between the latest opus and codex with codex on x-high thinking. Sometimes I do get solution from codex that is impressive because it discovered an edge case that Claude missed.
I did notice that codex - like Claude - is now better about auto delegating to agents for keeping the context focused and agents in parallel.
Yeap, it sounds like a big rant with multiple exclamation marks. Having both is a way to go. Recently I purchased a new laptop and thought should I go full Wayland? No way. I started with X11 and then added Wayland. Things break on Linux. You need a stable display server where you can still open a browser, and that is X11. Most of the time, I stay on Wayland until it breaks.
I cannot agree more though I have little experience in open source. I knew that Korean environment for open source software would be touch before coming back from Europe, it seems much easier to target international traction rather than focusing on domestic interest.
Personally, I'd like to know, since you have been active in Korea, if there is any groups that I can attend to.
Given that subagents have different thinking/effort behavior from the main agent and very limited control on that front (I’m not completely sure about this but see https://github.com/anthropics/claude-code/issues/14321 and I’ve also noticed very different behavior when the same prompt is used in the main agent or passed to a subagent), I’m not sure this skill will be the same.
Nice! You found the no-code option that just has the outer agent perform the duties of the workflows that cook describes. It's a bit experimental (the whole thing is really), but it would be nice to get some folks impressions of whether this works well as a pure skill or if y'all find the deterministic nature of the cook script improves reliability.
One question. Sonnet for tool use? I am just guessing here that you may have a lot of MCPs to call and for that Sonnet is more reliable. How many MCPs are you running and what kinds?
reply