I know someone who gets sycophantic answers from AI at a rate that I find awe inspiring; they like it, I find it sickening. I almost never get those types of answers. I'm not entirely sure what the difference is, probably the type of questions being asked, the way it's written, some susceptibility that is detected and the statistical token generator plays to the audience. Maybe emotional resilience and clear thinking has become an important skill in working with your tools so they don't take advantage of you.
The visual diff harness was probably how they got rid of a lot of visual bugs, just tell the LLM to keep going until the pixels match exactly as the verification criteria
If someone recreates Amazon's logistics and distribution systems they could try to compete with Amazon? But they'd also need the connections, distributors, transportation, etc. same with banking software, you need capital to be a bank not just software, and if they have the capital then the technology is working we intended making it easier to make new things and innovate, or at least just compete?
Your comment only makes sense in context if you believe in a deity who is too dumb to understand the difference between cr*p and crap. I for one do not worship a Bayesian spam filter.
My wife has some severe challenges (hormonal and otherwise), so I have changed almost all diapers, and work part time/nights as a software developer purely for the fact that I need to be available to take our child regularly throughout the day, at one point I was full time childcare and job. My wife has a free pass to go on day trips and climbing excursions for her mental health. I guess the point is, to find someone who genuinely wants to help and participate, and find something that works for you. It's such a huge part of life, it's important to get the balance right. That's a difficult thing to do, but knowing what someone's core beliefs about family, responsibility, and expectations is important.
My optimistic take on this is that they are still in process. One or two man team might be able to code as fast as 6 or 10 man team in some cases, but the design process takes just as long. GTA6 has a crazy amount of resources and programmers on it, but still takes years to come out-- because they have to balance, develop content, playtest and find bugs, etc. even if bug fixing was instantaneous and thinking of something made it happen, it would still take a lot of time. So someone making something great as a solo developer is still going to take as long as a small team of people making something great before. Which is years.
My philosophical take is that there are different types of coders, the ones who did it because they wanted to see their design be implemented and those who love the technical puzzle (with obvious overlap). The technical puzzle is taking a hit currently, but I think it will still exist in some form; the designer trying to get something implemented still loves the design work primarily which is sorely lacking in current LLMs, but if they don't have enough technical knowledge they will still get slapped in the face by technical gaps and bugs that LLMs make.
For corporate stuff, I think bureaucracy and issues with churn reduce the effectiveness of using an LLM because the most effective way might be anathema to corporate fiefdoms and structure. The churn is a problem for everyone though...
1. They don't exist, so if you own the game you still want it to work on your computer without maintenance updates
2. They still exist, so they don't want to have to update it every year because they can use that effort on making a new game and continuing to exist while still being able to sell from their existing catalogue because it still works
Either way it's in a game developer and gamers interest to have stable platforms
Someone I know who did a lot of consulting said consulting was very easy 1. Go in and talk to employees about what is wrong 2. Tell management what the employees said without mentioning it came from the employees (so that management wouldn't dismiss it out of hand) 3. Charge a lot of money so management felt like it was very valuable feedback
There have always been snake oil salesmen, for awhile they had to put the effort into knocking on your door peddling MLMs, now they're making more impressive snake oil, but vacuous, with LLMs.
I've always been curious about graph DBs and dabbled a bit in them, but for those who have more extensive experience in them-- are they really worth it? Is it that for small scale SQL is better and graph DBs really only matter at scale, or for specific use cases with highly connected data?
I tend to run it on High and then step it up for problems where I'm noticing it struggles, bump it back down after. Sometimes I accidentally leave a session in Ultracode for a day and wonder why things are taking so long, but generally happy with the results.
And makes it more expensive. There is the seen benefit and then the unseen cost. Every game released will have to account for the possibility of it, and will create issues for people who really didn't want those issues. After awhile people will forget there are associated issues and costs, but they will still be there.
What about the third group who mostly don't use ai for programming because the results don't seem to be worth it, like to understand their system, and can craft a more compact, succinct, and well organized system by themselves which they enjoy maintaining? If most of your system is boilerplate that can be generated by Claude, then maybe you're doing it wrong? I'd rather read a short story written by a great writer than a trilogy of novels by AI
YouTrack's search is one of the main reasons I use it. Nice query language to filter down on any fields, including custom fields, never had an issue finding things. It's great. With the number of useless search functions in so many products, I'm happy that at least my issue tracking does it right.
Strangely enough (or maybe to be expected), I'd say that at least on the Christian and Jewish sides, it's led by people who have no sincere belief in the respective religions, but hijack it for their personal power. Reminds me of Germany in WWII where Christian symbolism with "Positive Christianity" was used until it was no longer useful then they went full pagan (gottgläubig and other movements) because the sincere Christians opposed them. This administration is as likely to quote Jesus with "love thy enemy" as Germany was in 1942.
So true. And I'll add, no matter how trustworthy you believe the other party to be based on reptutation, relationships, or otherwise-- they should understand requiring assurances. The worst backstabs are from the people you know and who should know better. And a lot of people will justify it to themselves if they get in trouble. They will continue telling themselves that they are fundamentally good people and it just didn't work out as they rip you off for a lot of money. If they say the equivalent of "why don't you trust me?" that's a red flag.
I watched an interview with a retired British military guy who said that the radar destruction does complicate things, but the US still has the other AWACs, so there is still early warning and visibility, just complicates things and reduced range/more risk.
It seems to me that if someone can read and think critically-- they can RTFM and get much better much quicker at computers and AI than people who spent all their time tapping an ipad to watch the next video.
I have a very similar situation. Except it isn't even a ticket, just an export of a very long "conversation" with ChatGPT with a vague indication that this is what needs to be implemented. When questioned about it, the person insists they completely understood it before but just forgot after a few days. Sometimes the prompts are removed. Lots of contradictory material in it, some doesn't make sense even in context. Very difficult to figure out what is wanted.
I would encourage my competitors to use AI agents on their codebase as much as possible. Make sure every new feature has it, lots of velocity! Run those suckers day and night. Don't review it, just make sure the feature is there! Then when the music stops, the AI companies hit the economic realities, go insolvent, and they are left with no one who understands a sprawling tangled web of code that is 80% AI generated, then we'll see who laughs last.
Slightly tangential but recently I've gotten into the Ilwinter Game Design games Dominions 6 and Conquest of Elysium 5. I was surprised how similar but how different they are to Europa Universalis and Civilization respectively. Very interesting studies in horizontal game design where every faction has dramatically different gameplay strategies.