No matter how you slice this apple, it's going to be lopsided. The real problem is that true learning is hard, ugly work, and the vast majority of people simply don't have the grit to choose friction over shortcut. Lord knows, I wouldn't have put in the grinding effort to learn how to code if I could have just bot-it.
To make matters worse, you have advertisers masquerading as influencers pushing the notion: if you're not shipping 10 features a day, you'll be left behind. It's a perfect damned if you do, damned if you don't situation.
My guess, is it boils down to legal liability. Every time I look into repurposing my old smartphones, I inevitably go down the "well, it probably won't burn my house down… but. " It's the same reason why I don't use Molex-to-SATA power adapters, even though I could save a few bucks. Regardless, Samsung ghosting iFixit is inexcusable.
Yup. Last week my Ultra account got ToS-banned from both the Gemini CLI and Antigravity simply for using OpenCode. Try as I might, I haven't been able to resolve the issue. I can technically still use the Gemini web/app, but it's remarkably terrible in just about every conceivable way. A truly impressive feat in itself.
As of now, yes. However, a few months ago it was mentioned that Google is working on increasing the limits for Pro/Ultra subscribers. But if I can't get this ToS ban sorted out, I assume it'll follow my account when that update lands, and I'll end up being banned from AI Studio as well.
If the benchmarks are to be believed, and assuming ~0.93 recall is "good enough" for the use case, this vector DB is seriously fast: about 5x the queries/sec of OpenSearch and 19x Milvus.
NOTE: The script is broken, DO NOT ATTEMPT TO USE THE SCRIPT NOW. Attempting to run it may get your account flagged stopping you from trying face verification either temporarily or permanently, forcing you to use your ID.
Literally the opposite though, as being able to see what it reads allows you to tell it to ignore certain files when you see it read the wrong one, and adjust the claude.md file to ensure that it does not read incorrect files given a specific input.
Jokes about vibe-coded CLI aside, I think that's the issue for me, the defaults are being tailored to vibe coders. (and the general weirdness of trying to fix it with verbose mode)
I like that people who were afraid of CLIs perhaps are now warming up to them through tools like Claude Code but I don't think it means the interfaces should be simplified and dumbed down for them as the primary audience.
Sure you can press CTRL+O, but that's not realtime and you have to toggle between that and your current real time activity. Plus it's often laggy as hell.
Yeah, these all sound like complete non issues if you're actually... keeping your codebase clean and talking through design with Claude instead of just having it go wild.
I'm using it for converting all of the userspace bcachefs code to Rust right now, and it's going incredibly smoothly. The trick is just to think of it like a junior engineer - a smart, fast junior engineer, but lacking in experience and big picture thinking.
But if you were vibe coding and YOLOing before Claude, all those bad habits are catching up with you suuuuuuuuuuuper hard right now :)
As a SE with over 15 years' professional experience, I find myself pointing out dumb mistakes to even the best frontier models in my coding agents, to refine the ouput. A "coder" who is not doing this on the regular is only a tool of their tool.
(in my mental model, a "vibe coder" does not do this, or at least does not do it regularly)
Well, the term lacks clarity and a shift of meaning.
If you define "vibe-coders" as people who just write prompts and don't look at code - no, they ain't coders now.
But if you mean people who do LLM-assistet coding, but still read code (like all of those who are upset by this change) - then sure, they always have been coders.
I was curious about the scale of 1TiB of text. According to WolframAlpha, it's roughly 1.1 trillion characters, which breaks down to 180.2 billion words, 360.5 million pages, or 16.2 billion lines. In terms of professional typing speed, that's about 3800 years of continuous work.
So post-deduplication, I think it's a fair assessment that a significant portion of high-quality text could fit within 1TiB. Tho 'high-quality' is a pretty squishy and subjective term.
> it can read my text messages, including two-factor authentication codes. it can log into my bank. it has my calendar, my notion, my contacts. it can browse the web and take actions on my behalf. in theory, clawdbot could drain my bank account. this makes a lot of people uncomfortable (me included, even now).
...is just, idk, asinine to me on so many levels. Anything from a simple mix-up to a well-crafted prompt injection could easily fuck you into next Tuesday, if you're lucky. But admittedly, I do see the allure, and with the proper tooling, I can see a future where the rewards outweigh the risks.
Best case, Google DeepMind cracks AGI by letting agents learn for themselves inside simulated worlds. Worst case, they've invented the greatest, most expensive screensaver generator in human history.
reply