matteocontrini

Copilot's main target is probably enterprises, who already pay per token with both Claude and Codex, on top of a per-seat subscription. With Copilot they get both Claude and Codex and many other models in one subscription. Also, per-seat price includes usage and the cost of extra usage is identical to going direct with model providers. I'd say it makes sense.

As far as I know, the DANE spec (RFC 7671) requires DNSSEC to be enabled, while MTA-STS does not.

I've run some benchmarks a couple years ago, I don't have them at hand unfortunately but off the top of my mind, seqread 4k produced around 1500 IOPS while seqwrite was like a third of that. The practical performance was abysmal, I moved PostgreSQL storage to a volume and it was very noticeably slower just by browsing the web app (compared to NVMe SSD storage).

For comparison, I'm now using UpCloud which uses network-attached storage for all volumes and easily hits 10k IOPS (up to 100k with some tuning).

I certainly may have missed something while testing this so I'm happy if someone else wants to contribute and correct me if I'm wrong.

Beware of Hetzner Cloud volumes, they're unusable for a database, they're too slow. I'm not sure what workloads people run on Hetzner but the low-performance volumes and unreliable load balancers don't seem like a good fit for real production stuff with traffic.

Because they also offer free DNS and email. There are no ads.

Finally? This content has been up since 2018.

The status page was updated 6 minutes after the first internal alert was triggered (8:50 -> 8:56:26 UTC), I wouldn't say this is too long.

VP9 and AV1 are less affected not because they're free and open source, but because they're backed by large-enough companies (Google) and a consortium that promised they won't claim royalties for the patents used in the formats. Companies outside Google or the consortium can still claim royalties, and indeed they do. See the Sisvel VP9/AV1 patent pool for an example of patent holders claiming royalties for technologies used in VP9 and AV1.

It would still fail if you were unluckily on the new proxy (it's not very clear why if the feature was not enabled, indeed):

> Unrelated to this incident, we were and are currently migrating our customer traffic to a new version of our proxy service, internally known as FL2. Both versions were affected by the issue, although the impact observed was different.

> Customers deployed on the new FL2 proxy engine, observed HTTP 5xx errors. Customers on our old proxy engine, known as FL, did not see errors, but bot scores were not generated correctly, resulting in all traffic receiving a bot score of zero. Customers that had rules deployed to block bots would have seen large numbers of false positives. Customers who were not using our bot score in their rules did not see any impact.