Given that MSFT is down just 1.5% pre-market after what surely must be one of their biggest outages in the past decade, no one thinks much will come of this.
Stalwart already has calendars and contacts. Zulip works great for Slack-style collaboration and has easy integration with many videoconferencing providers. OwnCloud is great for files and office-style collaboration. All can be integrated with LDAP.
Cool, let's just rip out existing infrastructure, retrain entire IT staffs on obscure products they've never touched and pray that they all just work. I'm sure someone in charge of a budget will just love the sound of that!
No, you don't just do the simplest possible thing and see if it's in some DB because it happens to be more accessible to LLMs, then call it a day and a call it a "discovery". More from the Bluesky thread:
> any archaeologist knows to triple check before saying something is "new"
There is lots of due diligence needed before proclaiming stuff like that. Not just in archeology, but in sciences in general. There is an expectation that you'll review what you put out carefully, not rush to publish as soon as possible, and review prior art. Not least because it's embarrassing as hell to accidentally claim to have invented/discovered something, but in reality someone else was clearly way earlier than you, you just didn't look closely/broadly enough before.
As a second thing, once you find out you're wrong, you generally want to retract something to save face, if you're a good enough human to be able to admit when you're wrong. The author's "What I've learned" remains "You can just do things" even though the top of the article now has a correction that the agents maybe "missed it while going through the literature".
> difficulty: not an archaeologist but a SWE cut the guy/gal some slack
Maybe don't publish archaeology "findings" and "discoveries" if you're merely a software developer. I don't go around publishing things about nuclear reactors, because it's not my area, I couldn't even review myself if it's right or not.
Finance is a whole industry and you will find all sorts of approaches, certainly including letting Claude run amok with your credentials.
You can certainly imagine very senior and powerful traders at GS demanding it. I'd be only slightly surprised to find that GS allowed it. The traders would have had more power than the IT people trying to forbid it.
In Android apps need to request location permission. You can reject it and/or uninstall those which request it.
Within the same profile, apps can communicate through local IPC though. Wouldn't surprise me if some SDKs use this to coordinate exfiltration of data between apps. I mean, tracking companies have even used localhost sockets to improve tracking: https://localmess.github.io/
I regret that we've moved away from a world where you could easily tell your device throw a privacy-preserving bone to pesky apps. ("Sure, you've got location access, but it'll only show my house, you don't get to see where else I go.")
Instead our ownership and agency has been sacrificed on the altar of "but BigCo doesn't like it because users can lie."
A compromise might be that only certain special classes of apps can get the "don't lie to me" status, where a bank's app has to prove it's a little different than some "tired of our website try our app" thing or the average shovelware.
Goldman is very unlikely to have decided proactively to cut off traders access, and it's much more likely there was an operational loss. What kind of loss? I don't know but consider:
1) Claude Code is only being taken away from traders.
2) Only traders have permission to send orders to the market and book client trades.
3) Claude code would probably have been running as the trader, under their account with minimal review.
If you run a coding agent in that environment it's only a matter of time until it enters a bad order or books a bad trade, and once that happens it's only a matter of time before management decides to take this kind of action.
Goldman is definitely not doing this for cost reasons. They can afford the tokens.
a) They are pulling it entirely rather than imposing a cap or enforcing the use of cheaper models. This would be a strange choice if cost was the only concern.
b) Famously, traders at Goldman are well renumerated. Given the costs of these people even small productivity improvements carry a large value.
c) It would be very difficult to determine in any kind of conclusive way that the benefits were smaller than the costs.
For all these reasons I find it totally implausible that this decision was driven by API costs.
Having sat in a trading seat at a GS competitor, I can second this. If a Claude Max subscription led to one better trade over the course of a year, there's an almost 100% chance that it would pay for itself. And consider that a trader at GS would be doing dozens if not thousands of trades per day (depending on the seat/product).
Definitely not using something like an Anthropic model for research, FWIW. The amount of data the LLM needs to consume to build context for even simple trade sequence comprehension makes it next to useless.
There are a litany of other mathematical and ML models that can more aptly be applied to the space.
But to answer your question more directly, yeah...there's no way in hell you'd let the questions your traders are asking in research out of the four walls of your building if you can avoid it.
Not sure how long you'll be able to sell compute to anthropic for. They are constrained right now but they have an insane pipeline of take or pay contracts, and if those are delivered they'll be drowning in compute in a couple of years time.
Look how incredibly vulnerable our software is, and then consider that our financial and service infrastructure is not being regularly hacked. This is despite several large well funded nation state teams working on finding ways to exploit them.
Why is that? Was it just restraint? North Korea didn't show a lot of that to Binance but perhaps they are leaving traditional infrastructure alone because it's harder to profit from.
Actually it seems somewhat remarkable crypto exchanges aren't hacked more often. I guess that's another message from this - somehow people can build secure infra from these apparently broken pieces. Perhaps there's hope.
Yes and no. I think parent is moving towards an interesting point.
Why haven’t these been operationalized? NK resorted to social engineering in their latest bitcoin heist despite there been a thousand holes in the system.
To me, this points towards these holes are near impossible for humans and traditional tooling to find and Pandora’s box has been opened, or that these holes are not open to abuse in practice.
We humans are vulnerable to anthrax or sarin as well, but countries exhibit restraint in using such agents, because retaliation would be gruesome. Having someone going full rogue with cyberattacks could even unite the US and China temporarily in order to whack them.
The game is not bad. I tried it out and solved the Paris case. I liked the style and the locations.
I don't think I had to actually use the LLM chat at all though? It felt like suggested questions were all that was required.
There's an element of "just go everywhere and click on everything" too. For example having to return to a previous location to find someone now has a vital clue for you on how to solve a new puzzle. I'm not sure how you are supposed to know you should to back there. That kind of gameplay isn't that much fun.
Thank you for playing it through. The Paris case is the first of a five-level training pack, it's meant to guide new players with a tutorial. The free questions really matter in the real cases after that, where the suggestions don't cover what you'll need. And very good point about going back to a location, will definitely fix it in the next version.
I'd guess that almost every CEO affected asks themselves whether they should be so reliant on Microsoft.
reply