Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

Post by aryehof » Mon, Jul 13, 2026, 7:11 AM UTC

oxzidized wrote: post #297

FridgeSeal wrote: post #290

Earlier quoted context omitted.

Amusing that you think businesses still have QA teams.

Parent comment said they end up "...pass[ing] it off to QA." Edit: suppose that very well could have been tongue-in-cheek. Side note: as someone who has been interested in programming for a while, but didn't end up in a software dev track in life, it's been pretty wild watching the ride you all have been going on lately. I used to be pretty bummed I didn't get to do that kind of work for a living, but lately I've bee…

Post by FridgeSeal » Mon, Jul 13, 2026, 7:17 AM UTC

palmotea wrote: post #324

FridgeSeal wrote: post #291

Earlier quoted context omitted.

> I just don't care anymore because it's not my responsibility or my code at all at that point Yep, 100%. Business has made it clear they don’t care, so there’s no point in burning one’s energy. Throw the whole thing on auto, check out, and go do something else during the day.

> Throw the whole thing on auto, check out, and go do something else during the day. If that's what you're doing, you're fucked (in today's society, at least). What happens to your job when they figure out that's what you're doing?

Post by palata » Mon, Jul 13, 2026, 7:33 AM UTC

azinman2 wrote: post #211

athrowaway3z wrote: post #124

Earlier quoted context omitted.

I bailed on Anthropic the moment they started blocking alternative harnesses like pi on their subscription plans.

If I were anthropic I’d force that too. They offer the harness and if they control the entire pipeline then they can optimize the entire experience. It doesn’t have to be nefarious.

Post by leptons » Mon, Jul 13, 2026, 7:42 AM UTC

drob518 wrote: post #260

twelve40 wrote: post #227

Earlier quoted context omitted.

it's a very handwavey way to "explain" anything. Yes, they make money. But they have competition. And if someone runs out of tokens and switches to deepseek or just goes for a friggin hike in the woods, that does not benefit them. If they get a public image of a ripoff that burns all shit on trivial tasks, that does not do them good either. So there is a limit to this "companies make money" thing.

Sure, fair enough. Clearly, if they increase costs by too much, people will go to their competitors, but those competitors also make money selling tokens, so the whole industry is incentivized to inflate token consumption up to the point of driving people to the competition. And nobody is incentivized to reduce token count. In fact, the one model with great price/performance is Deepseek v4 Flash and I suspect that th…

Post by prince005 » Mon, Jul 13, 2026, 8:17 AM UTC

KingFelix wrote: post #314

prince005 wrote: post #310

I have been using claude code for a big project for a while and I feel like I have optimized my workflow now. Brainstorm - Gemini/Antigravity Plan - Gemini/Antigravity Detailed Plan - Sonnet Coding - Fable Do not use any subagents, especially the default ones. They are dumb. The top level agent works well enough

Does your detail plan outline exactly what to implement/ lines of code to edit? I found if I get a nice detailed plan that sonnet is good enough to implement. Did you try that before and found fable better at implementing?