It _was_ fantastic. Then it transitioned to abysmal over night when they switched to usage based billing. Now, if you put the same 50 USD towards GitHub copilot compared to Codex, I’m pretty sure Codex gives you 20x the usage or something. Really sucks for us who are stuck with GitHub copilot at work for compliance reasons.
Which has really only been accepted because 99% of people don’t understand how it works. Hard to be outraged by something you can’t see or understand. In my book, the practice is akin to malware. I recently opened a website for an AI service in incognito mode, because I didn’t care to have it in my search results. Despite avoiding third party cookies here, the site still fired off a tracker to Meta, who then correlated my home IP address with my Facebook account, and filled my feed with ads for this AI service. When I was tracked like this despite a somewhat informed defense, which defense do normal people have against this? None.
Can I trust code I’ve written myself with no guarantees from the language? Maybe. Can I trust code written by dozens of other developers (and/or agents) working on the same project over multiple years? Definitely not.
Oh, I’ve tried that too. It will promise to keep it in English from here on out, then switch back to Chinese after two or three exchanges. When ever it needs to do a web search, it seems to load so much Chinese text that it forgets any language instructions. Just thought my experience yesterday was more to the point. Right now the chat is absolutely hopeless.
I finally uninstalled the app yesterday after giving it plenty of chances over several months. Yesterday, I asked it whether «DeepSeek has fixed the issue where it erroneously answers in Chinese?» and it answered in Chinese.
Not really comparable IMO. Astra and Fable are not the every day workhorse you reach for to do basic tasks (unless your company has fuck you-money), they’re the tool you break out when you need the absolute strongest performance. There are plenty of tasks where finding and fixing one or two extra edge cases saves the business a lot of money, even if the cost is high. The best example would be scanning for vulnerabilities, if these models weren’t kneecapped in that area.
I’ve been refreshing hacker news constantly for a week now waiting for v4 pro, after they stated it would follow «soon». I have learnt «soon» is a matter of definition.
This is awesome. I’ve recently set up my opencode to use 5.6 terra for my main agent, who delegates work to a 5.6 Luna coder agent. So far it seems to work well, and reduce costs a lot. With this price reduction, it will work a whole lot better. Perhaps I can get my github copilot quota to last the whole month now.
I really wanted to try it out, but I keep getting blocked by rate limit (opencode go). Can you guys get off it for a second so it can process my request? Thanks.
Only problem for me vs using your primary DB is that Redis has no redundancy unless you run it in cluster mode. For us that means when the kubernetes node restarts, availability degrades. Could of course enable clustering, but at that point it isn’t dead simple anymore. And using the DB is.
The stock market rewarded SpaceX with a record breaking IPO valuation for promises that it would too offer a thing that could be reverse engineered with just 25k accounts. Possibly in space. The stock market doesn’t care.
Thanks for the advice. I don’t feel like my job is that bad, honestly. I’m an IT consultant and there’s always just a little too much that needs to be done at my current client. I’m extremely motivated for the task though, and end up overextending time and time again. There are definitely aspects of the project that are stress inducing (big org, lots of meetings, lots of different consulting agencies).
Recognizable. I try to increase how much of my wage I save, in case I can’t continue working for ever.
My best answer for my own sake is just burnout, exasperated by some underlying depression. I can have good periods when job stress is low and I make good life choices. Incidentally, I had a blood test show borreliosis randomly 10 years ago, but doubt that’s relevant.
I've been on Grindr for years, and I know first hand that their support is as bad as it can get. _Seriously_. I know because they also have a big automated ban problem. In trying to fight their bot issue, they've started auto-banning accounts that trigger their filter in some way or another. I've been banned 4 times without cause. Each time you have to contact support, who seemingly are either unable or not allowed to answer with anything other than canned responses. Three times the support person realized the ban was erroneous and lifted it without further ado. One time the person affirmed it, all while refusing to break from the canned responses or provide any justification. Most frustrating experience I've ever had with a digital service.