Updog By Datadog lets you spot issues with Anthropic early, backed by real impact across Datadog customer base. No status page updates.
Read the original article
Comments
The great thing about LLMs being more or less commoditized is switching is so easy.
I use Claude Code via the VS Code extension. When I got a couple of 500 errors just now I simply copy pasted my last instructions into Codex and kept going.
It's pretty rare that switching costs are THAT low in technology!
By shermantanktop 2026-02-0316:06 It’s not a moat, it’s a tiny groove on the sidewalk.
I’ve experienced the same. Even guide markdown files that work well for one model or vendor will work reasonably well for the other.
The switching cost is so low that I find it's easier and better value to have two $20/mo subscription from different providers than a $200/mo subscription with the frontier model of the month. Reliability and model diversity are a bonus.
By davedx 2026-02-0412:21 Yes that's exactly what I have too.
Which is exactly why these companies are now all focused on building products rather than (or alongside) improving their base models. Claude Code, Cowork, Gemini CLI/Antigravity, Codex - all proprietary and don't allow model swapping (or do with heavy restrictions). As models get more and more commoditized the idea is to enforce lock-in at the app level instead.
FWIW, OpenAI Codex is open source and they help other open source projects like OpenCode to integrate their accounts (not just expensive API), unlike Anthropic who blocked it last month and force people to use their closed source CLI.
By bloppe 2026-02-0316:38 I only integrate with models via MCP. I highly encourage everybody to do the same to preserve the commodity status
By LetsGetTechnicl 2026-02-0316:30 Using "low cost" and LLM's in the same sentence is kind of funny to me.
I genuinely don't know how any of these companies can make extreme profit for this reason. If a company makes a significantly better model, shouldn't it be able to explain how it's better to any competitor?
Google succeeded because it understood the web better than its competitors. I don't see how any of the players in this space could be so much better that they could take over the market. It seems like these companies will create commodities, which can be profitable, but also incredibly risky for early investors and don't make the profits that would be necessary to justify the evaluations of today.
By crazygringo 2026-02-0317:201 reply > If a company makes a significantly better model, shouldn't it be able to explain how it's better to any competitor?
No. Not if it's not trained on any materials that reveal the secret sauce on why it's better.
LLM's don't possess introspection into their own training process or architecture.
That's my point. Anything that could exist that's significantly "better" would be able to share more about its creation. And anything that could be significantly better would have to be capable of "understanding" things it wasn't trained on.
By crazygringo 2026-02-0319:03 That's not true. There are a million ways to be "significantly better" that don't involve knowledge about the model's creation. It can be 10x or 100x or 1000x more accurate at coding, for example, without knowing a single thing more about its own internal training methodology.
By Smaug123 2026-02-049:11 Could you share anything about your creation, without having been to school where we taught you what the answers were? Can you deduce the existence of your hippocampus just by thinking really hard?
> It's pretty rare that switching costs are THAT low in technology!
Look harder. Swapping usb devices (mouse,…) takes even less time. Switching wifi is also easy. Switching browser works the same. I can equally use vim/emacs/vscode/sublime/… for programming.
By pchristensen 2026-02-0316:271 reply Switching between vim <-> emacs <-> IDEs is way harder than swapping a USB (unless you already know how to use them).
good point, they are standards, by definition society forced vendors to behave and play nice together. LLMs are not standards yet, and it is just pure bliss that english works fine across different LLMs for now. Some labs are trying to push their own format and stop it. Specially around reasoning traces, e.g. codex removing reasoning traces between calls and gemini requiring reasoning history. So don't take this for granted.
By crazygringo 2026-02-0317:22 I dunno. Text is a pretty good de facto standard. And they work in lots of languages, not just English.
By jononor 2026-02-047:22 You would have to buy said USB device and get it to your location. Switching WiFi is only easy if you mean on a single machine/gateway. Swapping the WiFi network equipment in an office is considerably more involved, depending on the desired configuration.
By amelius 2026-02-0316:57 You make it sound like lock-in doesn't exist. But your examples are cherry picked. And they're all standards anyway, their _purpose_ was for easy switching between implementations.
By NicuCalcea 2026-02-0316:271 reply Most people only have one mouse or Wi-Fi network. If my Wi-Fi goes down, my only other option is to use a mobile hotspot, which is inferior in almost every way.
By oneeyedpigeon 2026-02-0317:202 reply > Most people only have one mouse
Tell me you're not a Mac user without telling me you're not a Mac user...
By NicuCalcea 2026-02-0318:55 Thankfully, not a Mac user, or even a wireless mouse user.
By crazygringo 2026-02-0317:231 reply Huh?
By oneeyedpigeon 2026-02-0317:27 The default Apple mouse needs a backup because it still cannot be charged and used at the same time.
By whatever1 2026-02-0316:38 I mean sublime died overnight when vscode showed up.
By davedx 2026-02-0412:22 Huh? I have the VSCode extensions for both. Switching is a couple of mouse clicks and copy paste.
By falloutx 2026-02-0317:38 on some agents you just switch the model and carry on.
By benterix 2026-02-0318:24 Except Kimi Agent via website is hard to replace - I tried the same task in Claude Code, Codex, and Kimi Agent - the results for office tasks are incomparable. The versions from Anthropic and OpenAI are far behind.
Their GitHub issues are wild; random people are posting the same useless "bug reports" over and over multiple times per minute.
Gives you a good window into a vibe coder's mentality. They do not care about anything except what they want to get done. If something is in the way, they will just try to brute force it until it works, not giving a duck if they are being an inconvenience to others. They're not aware of existing guidelines/conventions/social norms and they couldn't care less.
By stevenpetryk 2026-02-0316:40 This sounds like a case of a bias called availability heuristic. It'd be worth remembering that you often don't notice people who are polite and normal nearly as much as people who are rude and obnoxious.
By Forgeties79 2026-02-0316:112 reply I am starting to get concerned about how much “move fast break things” has basically become the average person’s mantra in the US. Or at least it feels that way.
By embedding-shape 2026-02-0316:251 reply You're about a decade+ late to the party, this isn't some movement that happened overnight, it's a slow cultural shift that been happening for quite some time already. Quality and stability used to be valued, judging by what most people and companies put out today, they seem to be focusing on quantity and "seeing what sticks" today instead.
By Forgeties79 2026-02-0316:281 reply I’m not saying it’s a sudden/brand new thing, I think I’m just really seeing the results of the past decade clearly and frequently. LLM usage philosophies really highlight it.
By embedding-shape 2026-02-0319:051 reply > I’m not saying it’s a sudden/brand new thing
I was more referencing the whole "I'm starting to worry" while plenty of people been cautiously observing from the side-lines all the trouble "move fast, break things" brought forward, many of them speaking up at the time too.
It's been pretty evident for quite some time, even back in 2016 Facebook was used by the military to incite genocide in Myanmar, yet people were still not really picking up the clues... That's a whole decade ago, times were different, yet things seems the same, that's fucking depressing.
By Forgeties79 2026-02-0419:34 I’m starting to think this is unproductive tbh
By bandrami 2026-02-0322:58 Particularly since that mantra started around 2005 or so, which was exactly when Silicon Valley stopped creating companies that could run at a profit without a constant investor firehose.
Could it be that you're creating a stereotype in your head and getting angry about it?
People say these things against any group they dislike. It's so much that these days it feels like most of the social groups are defined by outsiders with the things they dislike about them.
Well not really, vibe coding is literally brute forcing things until it works, not caring about the details of it.
By charcircuit 2026-02-0317:25 So manual programming. Humans don't always get everything perfect the first try either.
By qbxk 2026-02-0316:57 if history doesn't repeat, but it rhymes
does vibe coding rhyme with eternal september?
By falloutx 2026-02-0317:40 IF anything, this is good news for Anthropic, they can now bury every open source project with useless isssues and PRs
By soulofmischief 2026-02-0316:21 Are these superpredator vibe coders in the room with us right now?
By monsieurbanana 2026-02-0316:027 reply Wow are these submitted automatically by claude code? I'm not comfortable with the level of details they have (user's anthropic email, full path of the project they were working on, stack traces...)
By tobyjsullivan 2026-02-0316:08 Scanning a few. Some are definitely written by AI but most seem genuinely human (or at least, not claude).
Anecdata: I read five and only found one was AI. Your sampling may vary.
By prodigycorp 2026-02-0316:27 I consider revealing my file structure and file paths to be PII so naturally seeing people's comfort with putting all that up there makes me queasy.
By philipwhiuk 2026-02-0316:04 No, but they are submitted by the sort of people who will use AI to write the GitHub issue details
By xnorswap 2026-02-0316:49 I think claude code has a /bug command which auto-fills those details in a github report.
By embedding-shape 2026-02-0316:04 Definitively some automation involved, no way the typical user of Claude Code (no offense) would by default put so much details into reporting an issue, especially users who don't seem to understand it's Anthropic's backend that is the issue (given the status code) rather than the client/harness.
By lavezzi 2026-02-050:33 Nope, all user submitted likely with the assistance of Claude.
By petters 2026-02-0316:17 How could they be? Claude was down
and every single one of them checked "I have searched existing issues and this hasn't been reported yet"
A long time ago I was taking flight lessons and I was going through the takeoff checklist. I was going through each item, but my instructor had to remind me that I am not just reading the checklist - I need understand/verify each checklist item before moving on. Always stuck with me.
A few times a year I have to remind my co-workers that reading & understanding error messages is a critical part of being in the IT business. I'm not perfect in that regard, but the number of times the error message explaining exactly what's wrong and how to solve it is included in the screenshot they share is a little depressing.
By delaminator 2026-02-0317:121 reply Application Error:
The exception illegal instruction
An attempt was made to execute an illegal instruction.
(0xc000001d) occurred in the application at location.
Click on OK to terminate the program.
By beAbU 2026-02-049:51 Yes, and this is an example of a horrible error message that does not help the use one iota.
By kogasa240p 2026-02-0317:00 Some of them don't even have error messages.
By kogasa240p 2026-02-0316:51 Goes to show that nobody reads error messages and it reminds me of this old blogpost:
> A kid knocks on my office door, complaining that he can't login. 'Have you forgotten your password?' I ask, but he insists he hasn't. 'What was the error message?' I ask, and he shrugs his shoulders. I follow him to the IT suite. I watch him type in his user-name and password. A message box opens up, but the kid clicks OK so quickly that I don't have time to read the message. He repeats this process three times, as if the computer will suddenly change its mind and allow him access to the network. On his third attempt I manage to get a glimpse of the message. I reach behind his computer and plug in the Ethernet cable. He can't use a computer.
http://coding2learn.org/blog/2013/07/29/kids-cant-use-comput...
By ebonnafoux 2026-02-0316:39 It's wild that people check the box
> I have searched existing issues and this hasn't been reported yet
when the first 50 issues are about 500 error.
This is the kind of abuse that will cause them to just close GitHub issues.
Or they'll have to put something in the system prompt to handle this special case where it first checks for existing bugs and just upvotes it, rather than creating a new one.
By orphea 2026-02-0316:10 I'm not too empathic to Anthropic. They did it to themselves by hyping AI and attracting that kind of people.
And it's not like they have been taking care of issues anyway.
By echelon 2026-02-0316:02 The automation of the SWE.
By ddmma 2026-02-0316:01 should enable some kind of agent automation
By nerdjon 2026-02-0316:11 There has to be some sort of automation making these issues, to many of them are identical but posted by different people.
Also love how many have the “I searched for issues” checked which is clearly a lie.
Does Claude code make issue reports automatically? (And then how exactly would it be doing that if Anthropic was down when the use of LLM in the report is obvious )
By nhubbard 2026-02-0316:28 I've made a feature request there to add another GitHub Actions bot to auto-close issues reporting errors like this when an outage is happening. Would definitely help to cut through the noise.
By LetsGetTechnicl 2026-02-0316:35 That's what happens when people outsource their mental capacity to a machine
By cing 2026-02-0316:12 Github issues will be the real social network for AI agents, no humans allowed!
By hacker_homie 2026-02-0316:44 Couldn't have happened to a better Repo, I needed that chuckle.
By falloutx 2026-02-0317:39 Thats exactly what they Anthropic deserves (btw they cant even get Anthropic on github lmao, this must be the biggest company having to run with wrong ID on github)
By palcu 2026-02-0316:56 Hey folks, I’m Alex from the reliability team at Anthropic. We’re sorry for the downtime and we’ve posted a mini retrospective on our status page. We’re also be doing a more in depth retrospective in the following days.
