My only concern with Codex is that it's not possible to delete tasks.
This is a privacy and security risk. Your code diffs and prompts are there (seemingly) forever. Best you can do is "archive" them, which is a fancy word for "put it somewhere else so it doesn't clutter the main page".
Terragon is an alternative (hosts Claude and Codex using your OpenAI and Anthropic subscriptions, and also supports Google and Amp) that provides this functionality.
I use it because it works out cheaper than Codex Cloud and gives you greater flexibility. Although it doesn't have 5.2-codex yet.
Yes but if it's not getting removed at the origin... it's not fixing the actual issue of the context/conversation surviving past an explicit "delete" request. Also let's not forget that anyone proxying LLMs is also man in the middle to any code that goes up/down.
It's weird, suspicious, and plain annoying. I like the the tool and my tests have shown it to be very powerful (if a bit rough and buggy), but this is ridiculous - I won't use it for any real world projects until this is fixed.
Then again, I wouldn't put much trust into OpenAI's handling of information either way.
But since then the other countries learned that the US government could weaponize their USD holdings if they don't align. Central banks started accumulating gold to counter this.
Also, debt market is not the same as it was 5 years ago, Japan now has inflation (and they hold the biggest bag of US debt).
To add to this, USD lost 10% of its value this 2025 according to the DXY index. To be fair, it pretty much went to what it was worth before 2022, but the Fed has to be careful anyway.
Many things happened since 2020. It's almost 2026.
However, it only owns 3% of US debt; they are the largest non-US holder, but still a marginal holder. Basically, they deseated China for that spot of "Biggest But Still Small US 'Lender'". Both together are dwarfed by pensions, 401ks, and other US buyers and institutions.
https://www.visualcapitalist.com/charted-heres-who-owns-u-s-...
>To those of us who like Free Software because of the freedom it gives us, this is a severe regression.
It's fair to be worried about depending on LLM. But I find the dependance on things like AWS or Azure more problematic, if we are talking about centralized and proprietary
I would probably just use bson or gRPC. As o clarified elsewhere, I means JSON as an analogy. I want something that can be scanned and queried cheaply.
Imagine that you want to make a film that is an unholy amalgam of Scrooge, A Charlie Brown Christmas, Dead Poets' Society and The Breakfast Club. Imagine that your audience is oblivious to any nuance and you're not so creative, so you will need to employ the standard tropes of bratty prep school kids, mother whose son was killed before his time, bookish professor with a heart of gold and life lessons at the end for all our protagonists.
Trowel on the schmaltz like it's wet concrete and multiply the cringe by 1000. Now you have a decent description of this movie.
This is why I like Arch's Pacman a lot, and the reason why I avoid Debian derivatives.
That `totallysafescript.sh` could at least be inside of the package manager scope. Most of the times someone already did it, and published it to AUR.
IMO the reason why there are so many people running random scripts in Ubuntu/Debian is due to how more difficult/inconvenient it is to get a dpkg .deb when compared to a PKGBUILD file. Same for MacOS, in which you have to either rely on Homebrew wizardry or just running the script
> That `totallysafescript.sh` could at least be inside of the package manager scope. Most of the times someone already did it, and published it to AUR.
The AUR is still not as good as proper package management and shouldn't be considered a stable or reliable method of software distribution at scale.
>I am also a freediver, and it is well known that hyperventilating before holding your breath is a deadly thing to do in the water, because it can cause blackout- and that seems to be what people are (incorrectly) doing here.
Coincidentally, Wim Hof and his technique came out in a conversation with a friend last night, and when he mentioned that hyperventilating was a big part of it I told him that it was a contraindication for epileptic people like me.
Actually, they diagnosed me by wiring me to an EEG machine while hyperventilating on purpose. I lost consciousness in the middle of the study.
Not the same, I know, but it's relevant still.
Also, there's a post from less than 2 weeks ago about it[2]
[1] https://developer.mozilla.org/en-US/docs/Web/API/HTML_Saniti...
[2] https://news.ycombinator.com/item?id=46198606
reply