Crowdstrike crashed 8 million+ machines and broke many so bad they didn't fix on restart. Their stock is up 3x since then: https://en.wikipedia.org/wiki/2024_CrowdStrike-related_IT_ou... . I don't understand it but I also wouldn't bet on anything changing from this outage.
Businesses rationally won't switch because of one outage (even a bad one) because switching costs for a lot of places will be astronomical.
So again rationally this shouldn't affect the stock price much.
However repeated disruptive outages every few weeks/months (à la GitHub) is a different story, and there's also the invisible effect of businesses maybe being less likely to choose Microsoft in the future
It must be 15–20 years now that Mimecast has been offering a protective layer around email services like Microsoft Exchange and Microsoft 365. Even today, you can see companies that are still able to keep their email running during Microsoft outages because they have Mimecast's email continuity service in place. It shows the value of having that extra layer of resilience.
If the downtime persists for more than 72 hours some will switch as they need to conduct their business , whether its email/github etc.
However as long as the outages are more like a snowday very few of the big orgs will have the inclination to get back into the business of self-hosting for accountability/price/biz inertia reasons.
A week long outage though , yeah at that point the decisions becomes a nobrainer and not even network effects will prevent the migration.
Even 72 hours isn’t enough - how will they conduct business with anyone else if they are still down and how will they get their old emails to resume conversations and how will they transfer their known email addresses or inform others of their new email addresses? None of that is cheap or easy.
Having an outage, fixing it, and then not having outages in the future, may be a positive signal compared to no outage ever, because you assume it will happen and the recovery time and process is unknown.
Regular businesses sure, but governments, public and essential services should have different criteria imo and should rethink their reliance on these services.
> switching costs for a lot of places will be astronomical
Switching to what though? It's not like we didn't have outages before SaaS. It just happened at different times throughout the year in stead of all having an outage at the same time.
I feel like the big difference right now is that management can't call the EoD for progress updates every 10 minutes, they just have to assume that someone at Microsoft is working on fixing the issue.
Indeed, realistically in 2026 switching from Microsoft to Gsuite, those are the only two things I've ever seen companies use, and Google doesn't have 100% uptime either.
So yes that's another argument to not do anything and stick with Microsoft unless things become terrible
I wish it was always my choice. The introduction of internet to the underground in London, has allowed others the choice of holding their conversations loudly within close proximity to me. I have no wish to know why you have fell out with your best friend, I'd prefer silence.
I've tried and tried to get an LLM to delete code, it couldn't do it. I knew a file was 40% bad so what I ended up doing was deleting the file, then asking AI to create the missing file. That's how I got AI to delete code :)
Could it be possible, these firms are optimizing for two things: a) Better performance. b) Gathering data from you to further improve performance later. I've also found the huge amount of planning rather than iteration frustrating. I've felt like I'm teaching a junior!
I think they simply optimize around E2E benchmarks, none of those benchmarks is designed as multi turn assistance to the user, but going from a prompt straight to the final solution.
Exactly. How can "we" develop and encourage benchmarks for multi-turn user assistance?
That is what I want.
I feel like the models and harnesses push much too hard against this workflow -- that they push you towards letting go and vibe coding, with only your discipline (and desire for a quality and maintainable product) holding it back.
I think they are optimizing for one-shot performance because that will drive usage. They can’t afford to look bad in the benchmarks. And if that means consuming an order of magnitude more tokens, well, that’s good for business, too.
I built a passion reference site. A large part of that passion came from knowing and talking to the people I was helping. One person emailing or saying thanks would later help power me through to create more useful articles. Enriching openai/claude/ms/google and no thanks from an individual, has disincentivized me from writing more.
Same here. People knew the website and it was immensely flattering to meet users in the wild. It motivated me to really sweat the small stuff, because people noticed. Now I'm just feeding the slop machine, and it feels pointless.
Is it about the users or the data the users generate. Pretty easy to see the day devs are replaced by the data they themselves generated. Companies are only going to get one chance to grad this data. Similar to the internet cutoff.
reply