[udev4096]

OP should've been more specific. HFT firms, not any other finance companies, probably have a lot more exciting work due to the nature of reducing latency using all sorts of novel techniques.

I wonder if they disable all the fancy exploit mitigation protection in linux kernel just for a tiny performance hit

[nly]

Most of them simply bypass the Linux kernel altogether

Processes reading and writing directly to FPGA/NIC ring buffers.

Shunning TCP in favour of UDP based protocols that are easy to optimize for your particular usecas in userspace.

Removing cores from the Linux scheduler entirely and pinning processes to those cores.

This stuff isn't even novel, it's been standard practice for a couple of decades.

[deivid]

Some jobs at HFT deal with a lot of this fun--I was doing Linux at one for 6 years.

A lot of jobs are extremely mundane though, compliance, regulations, legacy code bases, etc.

Yes, all mitigations get disabled

[cduzz]

Of course the mitigations get disabled.

What's the threat model where your HFT application's running hostile / untrusted code?

I'd like this stuff enabled on my desktop because I'm not sure what hideous javascript is being dumped into my browser by some advertising network.

But my trading platform? If the badguys are able to execute these attacks there, it's because they've got full access already.

[n4r9]

Mother capitalism deems that our brightest young minds best serve humanity in two tasks. Keeping the public passively scrolling, and moving money at speed to make wealthy people more wealthy.

[eru]

Actually, not. These market makers are often prop shops. That means they use their own fund (prop = proprietary) to do the trading. They can do that because they don't need much capital to run.

So the story here is that over the last twenty years they stole the lunch from the traditional market makers like eg banks.

Of course, they got rich in the process. But they started from relatively modest means, compared to the companies they took on.

Michael Lewis's 'Flash Boys' is an hilarious account of this process. Well, it's involuntarily hilarious, because to tell his story, Lewis needs to cast Goldman Sachs (!) and other big banks as the victim. See the rebuttal 'Flash Boys: Not so fast' by Peter Kovac for more insight.

[leg100]

None of that is contrary to "moving money at speed to make wealthy people more wealthy".

[eru]

You make new people wealthy.

[n4r9]

Perhaps some start this way. But in terms of the general trend of talented engineers and mathematicians being sucked into this quant vortex, it is a matter of making wealthy people wealthier.

[lotsofpulp]

Automation in trading makes all investors wealthier via lower fees. Trading costs basically nothing nowadays, and that is because far fewer people are employed to do it.

Obviously, the people who own the automation will want a cut of the rewards, like any other business.

[patmorgan23]

Automation in trading != HFT algorithms

Obviously NASDAQ and electronic trading systems are a good innovation. But firms basically doing arbitrage or exploiting uneven network latency are not that economically productive.

[eru]

And Jane Street isn't a classic HFT either. Speed isn't their differentiating factor (or at least wasn't in the past).

[rank0]

Absurd statement. Use your big brain CS mind for a second. This is you:

> Inefficient market spreads and network latency is not worth remediating.

[kqr]

Tighter spreads and higher liquidity is not economically productive? I can see arguments both ways.

[deepsun]

Some fraction of young minds, not all. I was happy to work at a small aerospace company with extreme concentration of brightest minds. Only because they loved the domain, and didn't mind a salary cut. What a joy and relief it was for me after FAANG!

[hereonout2]

Possibly you didn't mind the salary because you'd already worked at FAANG?

[deepsun]

No, I eventually left because money, I needed to save for a house. Most of the staff were locals, so already had own/inherited property to live in. After FAANG it was new to work with mostly locals, way more stories about the surroundings.

[andrepd]

> Only because they loved the domain, and didn't mind a salary cut.

Yes, so it means GP is right! Modern capitalism in tech is about rewarding the two aforementioned tasks.

[thom]

Hey, some of them are working tirelessly to ruin sports.

[actionfromafar]

Sports is doing that to itself, but I assume you mean betting, which really sucks the fun out of a room.

[amelius]

> Sports is doing that to itself

No, sponsor contracts, advertisements.

[udev4096]

Absolutely. The moral aspect is certainly questionable. Although, I wouldn't say "all brightest minds" are going to neglect their moral concerns for getting rich

[eru]

At one point, Jane Street had a lot of the effective altruists flock to them to 'earn to give'.

[n4r9]

To be honest, even this is morally questionable. It makes superficial sense in that someone else will do the work if you don't. But this happening on a large scale is still a drain on talent that could hopefully be used for work of greater social value.

[kitd]

With the "moving money at speed" part in the highly-optimised form of online betting.

[jrockway]

There's also electronic medical records in there somewhere.

[davesnx]

this is a good naval-style tweet, well done

[vasco]

Is the problem with the system or with the minds? The minds that want to scroll are the same as the ones that make money on the scrolling, that made the scrolling itself, and that made the system we're in. Why is it that defeatist comments always focus on the capitalism part and not on anything else? I don't think it's perfect like we aren't perfect but unless you have some particular suggestion this type of comment just reads "boohoo the world is bad and it's not my fault".

[Capricorn2481]

> Why is it that defeatist comments always focus on the capitalism part and not on anything else

Because endless growth is the only reason these once fun spaces have been hyper focused to be as addictive and stressful as possible to the "whales" of scrolling. That's why, when their own internal reports say "people spend unhealthy time on our platform and it's making them unhappy," it gets passed up the chain of command and whittled down by internal incentives until it dies as an issue.

Individuals hold some blame, but to put most of it on them is to ignore what growth demands. You're supposed to doomscroll and engage and worry. That's the business model. Facebook is in the same business as Cigarettes and Casinos. When I see someone on an air tank playing slots, literally crying when they spend their last dollar, I will not waste my breath blaming them. Just like I won't blame the doomscroller, anxious that they need to stay "informed," who hasn't met the basic needs in their own life.

> The minds that want to scroll are the same as the ones that make money on the scrolling

No? Where are you getting this? I don't think the people guiding these companies want to spend 6 hours scrolling TikTok. This is not the way most people live their lives.

[vasco]

> No? Where are you getting this? I don't think the people guiding these companies want to spend 6 hours scrolling TikTok. This is not the way most people live their lives.

I meant they are all humans. We're all sort of the same. If you disagree just think of your opinion of any other species, or about a group of people a thousand years ago, and you see what I meant.

[secondcoming]

Not HFT, but we disable those on our cloud VMs

[fuzztester]

some use a fork of rust with borrow checking disabled.

go fish

[francasso]

Would they also change the aliasing assumptions to something close to C/C++? Otherwise I imagine it would be relatively easy to make mistakes and get "surprises" at runtime thanks to the optimizer.

[shepherdjerred]

Isn’t borrow checking only compile time?

[SkiFire13]

Yes, but sometimes it forces you to write slightly slower code that can be proven safe.

[spoiler]

You don't need s whole compiler for that... You can use `unsafe`. Sometimes you don't even need that either!

[andrepd]

> forces you

Definitely doesn't, you can just slap unsafe and manipulate raw pointers if that's what you want