I can't see why anyone still chooses Claude. Codex outperforms it in most respects, and its quotas are about ten times larger. A $100 Codex plan gets me through the whole week with 6–12 hours of coding per day.
I found GPT 5.5 is pretty solid, but I keep getting impressed by opus. It's tracked down some insane stuff while I look away during a meeting. 5.5 is way closer than previous OpenAI models to Anthropic IMO.
These things are so tricky because everyone has a seemingly conflicting experience. Part of the fun I guess!
I've never actually run into the issues that people talk about online, like Claude suddenly getting dumb or running out of usage. So there's just not a lot of incentive for me to shop around. I've used Amp a bit, and it's quite nice, but a bit more expensive without the subsidized subscription.
One reason might be that Claude Opus 4.7 thinking benchmarks better on Arena Coding at https://arena.ai/leaderboard/text/coding ... hopefully that effectively assesses correctness. It doesn't account for reliability though.
You get a discount for paying for a full year on Teams and Enterprise can involve contractual obligations. It's a lot of effort to get buy-in to change providers and to shift an entire organization. The winds change frequently in this space and the pain needs to get to a certain level before it's worth rolling the dice.
Corporate policies and agreements. In large corporations, using external non-approved models with proprietary source code is a good way to have significant career issues.
Wow, I'm really surprised. I tried deepseek (their best model, through the official API). Its extremely cheap, but its clearly not as good at programming as Opus 4.7. It seems nowhere near as good at making high level design choices. Deepseek also seems to get stuck in whack-a-mole fixing loops much more than opus. I stopped it at one point, and asked opus to solve the problem it was trying to solve and it saw the solution immediately.
I was running deepseek through claude's code agent harness. Maybe it works better through a different tool?
I've given V4 Pro some curly things and I was impressed at how it figured them out. I agree high level design is not its forte. But it sat in a loop and dogmatically debugged a crazy dependency issue to come to the right answer over the course of 15 minutes which impressed me.
interestingly I had the same experience, and weirdly it's in part because it is clearly less intelligent. It's more of a mechanistic tool just doing what I ask (but still very smart and very competent about it) and less trying to win a nobel prize with each answer. Turns out I actually like that.
You're assuming the elevated error rates are due to the system being overloaded. We have no evidence this is actually the case. Its much more likely due to a simple misconfiguration or failing router or something.
so, all those CEOs moving all those remaining engineers to be dependent on a cloud service to the extent that there's no local development capability are gonna appologize right
I can't see why anyone still chooses Claude. Codex outperforms it in most respects, and its quotas are about ten times larger. A $100 Codex plan gets me through the whole week with 6–12 hours of coding per day.
I found GPT 5.5 is pretty solid, but I keep getting impressed by opus. It's tracked down some insane stuff while I look away during a meeting. 5.5 is way closer than previous OpenAI models to Anthropic IMO.
These things are so tricky because everyone has a seemingly conflicting experience. Part of the fun I guess!
I've never actually run into the issues that people talk about online, like Claude suddenly getting dumb or running out of usage. So there's just not a lot of incentive for me to shop around. I've used Amp a bit, and it's quite nice, but a bit more expensive without the subsidized subscription.
Are you using Opus? Sonnet remains as useful as it was while Opus efficacy and token burn rate has soured over the last 4 months.
Same here. Works every time. Never ran into usage limits either.
Claude is the only AI coding tool I've found worth a damn. Without it I'd just do everything by hand save for a few bash scripts or whatever.
One reason might be that Claude Opus 4.7 thinking benchmarks better on Arena Coding at https://arena.ai/leaderboard/text/coding ... hopefully that effectively assesses correctness. It doesn't account for reliability though.
You get a discount for paying for a full year on Teams and Enterprise can involve contractual obligations. It's a lot of effort to get buy-in to change providers and to shift an entire organization. The winds change frequently in this space and the pain needs to get to a certain level before it's worth rolling the dice.
Corporate policies and agreements. In large corporations, using external non-approved models with proprietary source code is a good way to have significant career issues.
Claude Max 20x gives me unlimited (for my level of usage) Opus 4.7 - how much money do I have pay OpenAI for that?
I think it's impossible to say that codex x.y.z is better than Sonnet x.y.z, I used many "high" end models and they're just all good.
Claude is significantly better at Rust in my experience, and Rust is my favorite language to emit from LLMs.
Opus 4.7 + Rust is a killer combo.
because my shard isn’t erroring
I use Codex when Claude Code is down, and I only began using Claude when ChatGPT was down
yes codex is very fast, I go back to Claude for now
Corporate reasons. AWS hasn't opened codex models to everyone yet.
Because of marketing and vibes mostly.
Heck I prefer DeepSeek to both of those.
Wow, I'm really surprised. I tried deepseek (their best model, through the official API). Its extremely cheap, but its clearly not as good at programming as Opus 4.7. It seems nowhere near as good at making high level design choices. Deepseek also seems to get stuck in whack-a-mole fixing loops much more than opus. I stopped it at one point, and asked opus to solve the problem it was trying to solve and it saw the solution immediately.
I was running deepseek through claude's code agent harness. Maybe it works better through a different tool?
I've given V4 Pro some curly things and I was impressed at how it figured them out. I agree high level design is not its forte. But it sat in a loop and dogmatically debugged a crazy dependency issue to come to the right answer over the course of 15 minutes which impressed me.
You tried v4?
Yeah, v4.
I would have been much more impressed with v4 about 6 months ago. But I've been spoiled by opus 4.7. Deepseek isn't at the same level.
interestingly I had the same experience, and weirdly it's in part because it is clearly less intelligent. It's more of a mechanistic tool just doing what I ask (but still very smart and very competent about it) and less trying to win a nobel prize with each answer. Turns out I actually like that.
Sonnet is also throwing overloaded error.
My systems are hitting exponential delay retries, so this might not get better because retries overload things again.
> {'type': 'error', 'error': {'details': None, 'type': 'overloaded_error', 'message': 'Overloaded'}, 'request_id': 'req_ ...
I can see a weird spike in my cache hit-rate a few minutes before, so this might actually be some extra caching they have thrown in.
https://status.claude.com/
They're having quite the day for devrel..
Do they need a waiting list, or what?
Sonnet is giving an overloaded message as well.
I thought the deal with xai was supposed to solve this? Is this basically the adding lanes paradox?
You're assuming the elevated error rates are due to the system being overloaded. We have no evidence this is actually the case. Its much more likely due to a simple misconfiguration or failing router or something.
so, all those CEOs moving all those remaining engineers to be dependent on a cloud service to the extent that there's no local development capability are gonna appologize right
in a year or two when AI tool costs go from 5M per year to 15M per year...even then, maybe not.