The durability guarantees are similar--each workflow step is checkpointed, so if a workflow fails, it can recover from the last completed step.
The big difference, like that blog post (https://www.dbos.dev/blog/durable-execution-coding-compariso...) describes, is the operational model. DBOS is a library you can install into your app, whereas Temporal et al. require you to rearchitect your app to run on their workers and external orchestrator.
I for one think that Gemini 2.5 pro has become much more stupid than before. This isn’t for coding, just simple business type support. It keeps forgetting queries, making really obviously bad suggestions, simple mistakes etc etc.
It’s kind of funny, because they keep talking about how close we are to AGI, and in reality they keep making the models dumber (uh, I mean more efficient).
> Presteign did not care for the artists, musicians, and fops Olivia kept about her, but he was pleased to see a scattering of society notables this morning.
> There was a Sears-Roebuck, a Gillet, young Sidney Kodak who would one day be Kodak of Kodak, a Houbigant, Buick of Buick, and R. H. Macy XVI, head of the powerful Saks-Gimbel clan.
ChatGPT 5> Without adding third-party dependencies, how can I compress a Data stream with zstd in Swift on an iPhone?
(It auto-routed to its thinking model, took 25s)
> Short answer: you can’t. iOS doesn’t ship a public zstd encoder/decoder. The system Compression and AppleArchive frameworks only expose lzfse, lz4, zlib/deflate, and lzma. So with only Apple SDKs, there’s no way to produce zstd-compressed bytes.
>
> Two practical paths:
> 1. If zstd isn’t mandatory, use a built-in codec (lzfse or lz4 are fastest) via Compression’s streaming API. Example (pure Swift, no deps) that compresses an arbitrary byte stream:
>
> <code example>
> 2. If zstd is mandatory, you must embed zstd yourself. That can mean:
> - Vendoring the official C sources (libzstd) directly into your project and calling them via a tiny Swift wrapper/bridging header
> - Statically linking a prebuilt libzstd.a you compile for iOS
I think the useful takeaway here is that Top 1 operation is generally not a good idea, especially not for making judgements. This doesn't address the main points of the blog though.
It is especially stupid because there is nothing analogous to Tiananmen Square in the west.
On the other hand, have it write a dirty joke. It just wrote me a few jokes that silicon value wouldn't touch with a 10 foot pole.
Not sure about the utility overall though. The chain of thought seems incredibly slow on things that Sonnet would have done in a few seconds from my limited testing.
Actually there is, fire up OpenAI or Claude and ask it for crime statistics.
I did and it lectured me on why it was inappropriate to ask such a wrongthink question. At least the Chinese models will politely refuse instead of gaslighting the user.
No, you've got it wrong. If US models are suddenly required to praise their monarch, or hide his past affiliations or whatever, that warrants them more critique.
Chinese models aren't don't become exempt "because the US is also bad", they both rightfully become targets of criticism.
Other than that, testing the boundaries of the model with a well-established case is very common when evaluating models, and not only with regards to censorship.
At the cost of it being really obvious where you are.
However the bigger draw is probably high bandwidth two way communication globally. No need for an obvious route as you can use GPS to get near US waters before turning it on, while still being in control of location of delivery or even meet up with it on the open ocean.
Sending the position only requires a few bits, let's say 48. A position update requires even less, depending on how far it could have travelled since the last known position. At such low data rates you could hide the transmission quite effectively.
As a once off it’s not going to be investigated, start making regular trips and people are going to start looking for such signals. Short bursts strong enough to detected many hundreds of miles away inherently need to be fairly strong making them standout from the background noise for close receivers. You can similarly triangulate based on signal strength given some ocean ships or even cheap buoys.
Starlink needs to be detectable by satellites, but you can almost completely block the signal going in other directions.
SpaceX might already be sharing it’s data with coastguards though.
I also wonder if you could have a visible surface vessel (e.g. fishing boat) which acts as a navigation beacon for the sub. Sub can just follow the beacon without any active communication of its own. If enforcement appears, sub will destructively sink to avoid revealing the operation.
> Additionally, developers can also control moderation sensitivity with the `moderation` parameter, which can be set to auto (default) for standard filtering, or low for less restrictive filtering.
I played around with this last night and although it still sometimes refused to create images, it seemed to be significantly more lenient.
