- F7F7F7What are you doing with GPT Pro? I've compared it directly with Claude Max x20 and Google's premium offer. I just don't see myself ever leaving Claude Code as my daily driver. Codex is slow and opaque, albeit accurate. And Gemini is just super clumsy inside of it's CLI (and in OpenRouter) often confusing BASH and plans with actual output.
- Every plan Opus creates in Planning mode gets run through ChatGPT 5.2. It catches at least 3 or 4 serious issues that Claude didn’t think of. It typically takes 2 or 3 back and fourths for Claude to ultimately get it right.
I’m in Claude Code so often (x20 Max) and I’m so comfortable with my environment setup with hooks (for guardrails and context) that I haven’t given Codex a serious shot yet.
- Meh. When I see Developer Terminal I’m thinking more Mac OS Terminal where I live out my days and nights than Bloomberg’s Terminal.
I know Bloomberg’s is iconic in the financial world but that’s a different persona.
Also, before the responses to me start to pile up, yes: I am aware of the UNIX underpinnings that NextOS/MacOS relies on for Terminal and the influences thereafter.
- Since 2006 I’ve been on this same mission. Let us know when you’ve figured it out.
- Presumably the same affected units are part of the redundancy package. The article essentially says as much.
- It’s niche and limiting in the same way that Supabase and Firebase are niche and limiting.
- I’m probably not the right person for this but it’s perfect for home use. There’s a few OSS homelab dashboards build exactly for this type of thing. I run a Home Assistant one.
- It’s getting better on Claude specifically now that training cutoffs are starting to move beyond the end of 2023.
OpenAI models are a little less likely to trip up as long as you keep reminding it that it needs to account for v0.23+
- Claude uses Haiku to summarize and name all chats. Regardless of what model the user is using.
If people don’t think that Anthropic is doing a lot more behind the scenes they are borderline delusional.
- It’s retargeting and it happens much more often than you think.
Try the same thing at pretty much any e-commerce store. Works best if you checkout as a guest (using only your email) and get all the way up to payment.
A day later you’ll typically get a discount coupon and an invitation to finish checking out.
- Every time I type in cap case or use a 4 letter word with Claude I’ll get hit with the 1 questions survey.
More times than not the answer is 1 (bad, IIRC). Then it’s 2 for fine. I can only ever remember hitting 3 once.
- Couldn’t have said it better myself. I’ve cancelled my x20 two times now and they keep pulling me back.
- I was one of you two, too.
After a frustrating month on GPT Pro and a half a month letting Gemini CLI run a mock in my file system I’ve come back to Max x20.
I’ve been far more conscious of the context window. A lot less reliant on Opus. Using it mostly to plan or deeply understand a problem. And I only do so when context low. With Opus planning I’ve been able to get Haiku to do all kinds of crazy things I didn’t think it was capable of.
I’m glad to see this update though. As Sonnet will often need multiple shots and roll backs to accomplish something. It validates my decision to come back.
- For those of us who want our mobile devices to just be there when we need it...thank god there are no new animations. I don't need a shot of dopamine every time I open the Mail app. I just want to know that I successfully pressed the icon. Which is what micro interactions (aka small animations) are for. Feedback.
I hope the phone get's even more boring and uninspired next go around. Apple can afford to go back to the 'it just works' motto.
- Sounds great in theory. But this would put a serious dent in the Arduino opensource community and fragment support.
Arduino is the unifying umbrella that keeps everything together. With that gone the platform will surely lose.
- I'm a heavy Terminal user and run everything from local LLMs to full stack dev (react/python). I dibble and dabble in Blender, Unreal, and Logic Pro. I aimlessly browse the web looking for recipes, 3d printing files, shopping, HN, whatever. I'll occasionally spin up Age of Empire II locally or play some quick games via GeForceNow. I'm in full control of my Synology and Qnap NAS servers and the shit ton of media that's on it.
And I do all of that on my Mac. My 4090 rig is strictly for gaming with my son and my Proxmox Linux retired thin client rigs are for running my household on HA.
Please tell me what I'm missing out on by using a Mac OS device as my daily driver.
- Adjusted for inflation the Segway would be close to $10,000 today after taxes.
That price tag and the way overhyped lead up to it's unveiling combined to kill any chance the Segway had. Dean's (RIP, I think) vision might have had a chance if it wasn't the same price as a lightly used new-to-me Kia Sephia.
At even half the $5000+ price it would have found a lot more adoption. Tourism companies still use the shit out of them and once they start dumping them, I bet they'll be the cool thing to have.
- For non-vibe coding purposes I've found that my $200 Claude (Claude Code) account regularly outperformed my $200 ChatGPT (Codex) account. This was after 2 months of heavily testing both mostly in Terminal TUI/CLI form and most recently with the latest VSCode/Cursor incarnations.
Even with the additional Sora usage and other bells & whistles that ChatGPT @ $200 provides, Claude provides more value for my use cases.
Claude Code is just a lot more comfortable being in your workflow and being a companion or going full 'agent(s)' and running for 30 minutes on one ticket. It's also a lot happier playing with Agents from other APIs.
There's nothing wrong with Anthropic wanting to completely own that segment and not have aspirations of world domination like OpenAI. I don't see how that's a negative.
If anything, the more ChatGPT becomes a 'everything app' the less likely I am to hold on to my $20 account after cancelling the $200 account. I'm finding the more it knows about me the more creeped out and "I didn't ask for this" I become.
- I think you misunderstood op. Visa controls your free speech with regulatory pressure.
- He’s likely talking about Claude’s hook system that Anthropic created to provide better control over context.