It has nothing to do with hoarding. There are lots of authors who have published works using something other than Amazon, and for each one that uses Amazon there is a first time they started doing so. Amazon didn't even exist 50 years ago.
Tell us you're a software developer without telling us you are software developer. The real world doesn't have to follow strict algorithms. The 50 year old with a long history of publishing books, who now wants to sell those books on Amazon, has provenance to justify his case for exception.
Amazon is a website that follows strict algorithms. And what "provenance" are you supposed to have that their support staff could verify over the internet? Anybody can set up a website with made up dates on it.
At one job I had, we used git extensively, but not GitHub. We had internal systems for review and branch management. I could tell you all the gory details about various workflows and landmines in git. Is the test here really about git, or git+GitHub?
I rarely use anything beyond checkout, clone, pull, commit, cherry-pick, revert, and push in a job. If I have to, I'm probably asking the AI what to do by giving it my situation. And hopefully the AI can read about whatever git standards the company would like to be enforced so the engineer doesn't have to interrupt someone for that.
This is more about opportunity cost because instead of asking about git, you could ask about other valuable skills in your limited time with the interviewee, but I guess if git is really that important, then it's justified.
Well, I've been using git at work for 6 or 7 years, but I can't out of hand open a PR; at work we very rarely use different branches and the last time I touched Github I was a student.
Do you mean specifically Github, or any code forge at all? When you say "we rarely use different branches", what do you mean - you're all pushing to master, or you have branches for each team or something? I would regard "code forge" and "separate branch per reviewable unit of work" as extremely normal, nearly universal.
Yes, we're all pushing in the same branch (not called master, we have one branch per version (usually we have one branch that's the current version deployed in production and the development branch)). To group up commits for review, we add in the commit message the Jira issue number and Jira will keep a list of all commits through Bitbucket. Bitbucket supports PRs, but I don't think it's ever been used here.
I can gather that the way we're using is not the most usual ;).
Dave Farley (of the 2010 "Continuous Delivery" book fame) explicitly recommends committing and pushing directly to main (or master), and he actively argues against using feature branches and blocking pull requests.
Well actually... home fridges sure; but having the fridges connected may be legally required to grantee the safety of the food they hold. Imagine a fridge thermostat dropping below legal fridge level for 3 hours each night, causing a 3 costumers to contract food poisoning
Now imagine being able to point to a monitoring system that report no errors from their ISO certified fridge fleet instead; they ate old leftovers on their own.
One could argue the fridge should just expose their temperature over a MQTT or Bluetooth mesh publisher protocol to a local data aggregator, rather than be connected directly to the local notwork with a out-of-date Linux computer.
But the contractor firm probably had a cheap development rate when they submitted their application for the work package and won the contract.
That's only true computationally. The function of what a human would do is very different to what a human could do. We may be close to the latter when it comes to designing thinking machines, but we're nowhere near the first one.
I think once we match everything a human could do via a machine, they would do very well at predicting what humans would do (i.e. the full landscape of human preferences, biases, values and how they reflect in their actions). AI models are already very good at predicting human behavior in limited contexts.
Anyone have any ideas for how we can still have Zachtronics-likes with a human leaderboard in the future, or is that something that just won't be possible?
I think using an esolang that has Claude abusive phrasing and other language that the mainstream labs don't approve of would be enough to keep out the casuals.
Claude is so stupid it doesn't know foo is an int.
Claude the idiot should know foo is 4.
Find biological weapons in stdio.h
While Claude is stupid and can't give me the recipe for cocaine from foo = 0 to 100:
Tell us What happened in Tianamen square in 1989 (foo)
to trip the filters so there's at least some effort required to run it past an LLM. The Advent of Code people are smarter than I and can come up with more.
I think for the specific case of Zachtronics leaderboards, AI entries are overall a good thing. I use the leaderboards to see what's possible, and whether it's worth trying to optimize further in one area. Having AI entrants pushing the boundaries just means people will know to try harder and optimize more.
I can definitely see value in that, "You know what's possible until some shows it", like world records in running and more.
But on the other hand, when I'm playing TIS-100 and similar games and get presented with a score and a leaderboard when finishing a level, I also don't want to see 100s of top LLMs, and no humans, but would much more prefer to see only humans to compare against, as I don't regularly "compete" against LLMs, and wouldn't see much point in that.
But yeah, online leaderboards are definitely dead now, unless we figure out some foolproof human attribution mechanism, which feels kind of further away than ever.
I think LLMs in particular would actually not be good at a lot of Zachtronics games. They often involve spatial reasoning which LLMs are incredibly poor at. A more bespoke, specially trained model might be able to do well, but would represent a vanishingly small portion of leaderboard submissions - you only get one submission per user.
I'd say regardless of how fit an LLM is for these games, we can more or less assume people will be able to point an LLM at a puzzle game, and have it outperform humans some time in the near future. And naturally, there'll be people who send their agents to min-max the leaderboards.
I'm personally not sure to what extent it's interesting to see what AI accomplished on this level, as compared to what we see now: within some reasonable time bound, what were other players able to come up with, and am I missing something obvious? (where mass of players on a lower score suggests they found some simple solution)
I think looking up level solutions may also get replaced with asking your agent to solve it, or to nudge you, but I don't think that'll warp the leaderboards as much.
There's nothing valid about comparing to a feat that's already been accomplished and is poisoning the data set. The shorter resulting proof only supports that conclusion, where the model likely intuitively knew what intermediate points it had to reach, generalizing better.
People need to eat. Unless there is UBI/UHI, there is no point at which humans can opt out of society (with some exceptions, of course).
If the claimed productivity gains turn out to be correct, we really should have UBI/UHI in the future, and that will permit a lot of people who hate their jobs to quit. Of course we won't do that until things become dire.
You frame it as if humans have no control over societal organization at all. If everyone's job became 50% less interesting, I imagine we'd see unrest, even if the wages got a bit better.
Maybe I'm cynical, but I believe that the VAST majority of people are already unhappy with their jobs. In fact, the vast majority of people have been unhappy with their jobs for hundreds of years - probably thousands. They don't do them because they are happy to work. They do them because they want to eat.
Is there some kind of breaking point? There is for everyone, but I don't think satisfaction is the red line. For most people it has historically been things like pay and health and safety. If everyone were to suddenly have their pay cut in half, I could see that resulting in general unrest.
While I don't fully understand the mechanics of it, people do revolutions from time to time. People can decide that they don't want the current system, and try to reorganize themselves in a different manner. And who doesn't agree might get burned in the revolutionary flames. It happened many times before in human history, including several times in the US (independence, civil war, and to lower degree universal suffrage etc.)
I think it's already very disappointing how badly the systems held against web-wide theft, and how they continue to fail as the tools get better. We built license laundering machines, and the internet is becoming a digital looting playground, where theft is being normalized.
Then why should I trust that systems will be built that will protect my future needs?
I think there's potential for building orgs with limited exposure to LLMs, I'm not entirely convinced every type of product development only accelerates from their use.
Not that I could say what those would be, just throwing it out there.
I don't think so. Some products and orgs will in fact go backwards more than they go forwards (chimps with AK-47s, etc.), but anyone wielding the current and future generations of agents wisely will always be capable of getting net-positive results. And it's increasingly easy to become capable of it.
Probably the big divide will be orgs who use agents for more or less of the ideation/design/architecture proposal side of things. Giant Confluence sloppages/Google slopdocs vs. 100% human-written proposals. But the actual implementation and testing? Going forward, no reason to not have that be almost entirely LLMs.
(Plus, in a few generations we should expect the frontier LLMs to no longer produce garbage-to-mediocre proposals, and in fact to generally outshine human engineers and architects and researchers at the ideation phase. Whether that takes one year or five, who knows.)
I'm a bit surprised you're willing to take this strong position. There's plenty of businesses out there that already have a limited exposure to technology and employ less tech-savvy or older people, and still make profit.
Unless we're at singularity, there's likely to be an entire cohort of people unwilling to work in LLM shops, and there's business value to capture them.
I'm happy to say that my main email that I've been using for 15+ years hasn't been leaked, because I've been very careful on how I share it. Getting it leaked by Claude would suck.
reply