Normally it does fairly well but the guardrails sometimes kick even with fairly popular mainstream media- for example I’ve recently been watching Shameless and a few of the plot lines caused the model to generate output that hit the content moderation layer, even when the discussion was focused on critical analysis.

What I do remember unambiguously is being an active member of the site, contributing regularly and in good faith, being accused of spamming, and the general feeling of hostility that I got from the site.

My impression is that the site was actively looking for any possible reason to remove people from the platform. It’s their site to moderate as they wish, but that’s not a community I want to continue participating in.

It’s much shorter than my first book, Effective Haskell, and leans more advanced, especially toward the end. Although the format is puzzle focused I’m trying to avoid simple gotcha questions and instead use each puzzle as a launchpad for discussing how to reason about programs, design tradeoffs, and nuances around maintainability.

Anyway that was ages ago and we did it with like three people, some duct tape and a GPU, so I expect that it should work really well on modern equipment if they've put the effort into it.

I’ve also had experiences where I started out well but the AI got confused, hallucinated, or otherwise got stuck. At least for me those cases have turned pathological because it always _feels_ like just one or two more tweaks to the prompt, a little cleanup, and you’ll be done, but you can end up far down that path before you realize that you need to step back and either write the thing yourself or, at the very least, be methodical enough with the AI that you can get it to help you debug the issue.

The latter case happens maybe 20% of the time for me, but the cost is high enough that it erases most of the time savings I’ve seen in the happy path scenario.

It’s theoretically easy to avoid by just being more thoughtful and active as a reviewer, but that reduces the efficiency gain in the happy path. More importantly, I think it’s hard to do for the same reason partially self driving cars are dangerous: humans are bad at paying attention well in “mostly safe and boring, occasionally disastrous” type settings.

My guess is that in the end we’ll see less of the problematic cases. In part because AI improves, and in part because we’ll develop better intuition for when we’ve stepped onto the unproductive path. I think a lot of it too will also be that we adopt ways of working that minimize the pathological “lost all day to weird LLM issues” problems by trying to keep humans in the loop more deeply engaged. That will necessarily also reduce the maximum size of the wins we get, but we’ll come away with a net positive gain in productivity.

I see people using agents to develop features, but the amount of time they spend to actually make the agent do the work usually outweighs the time they’d have spent just building the feature themselves. I see people vibe coding their way to working features, but when the LLM gets stuck it takes long enough for even a good developer to realize it and re-engage their critical thinking that it can wipe out the time savings. Having an LLM do code and documentation review seems to usually be a net positive to quality, but that’s hard to sell as a benefit and most people seem to feel like just using the LLM to review things means they aren’t using it enough.

Even for engineers there are a lot of non-engineering benefits in companies that use LLMs heavily for things like searching email, ticketing systems, documentation sources, corporate policies, etc. A lot of that could have been done with traditional search methods if different systems had provided better standardized methods of indexing and searching data, but they never did and now LLMs are the best way to plug an interoperability gap that had been a huge problem for a long time.

My guess is that, like a lot of other technology driven transformations in how work gets done, AI is going to be a big win in the long term, but the win is going to come on gradually, take ongoing investment, and ultimately be the cumulative result of a lot of small improvements in efficiency across a huge number of processes rather than a single big win.

Maybe it’s my use of it, but I’ve never had it store any memories that were personally identifiable or private.

Linux has always appealed to tinkerers and that was always going to lead to some amount of fragmentation. I don’t think it’s a bad thing necessarily. For all of the complaints about it, systemd has unified a lot of things that used to be handled through desktop environments and made things less fragmented as a whole.

A beyond burger might be more like meat than a patty made from beans or lentils, but it tastes worse and has a worse nutritional profile. Beyond chicken isn’t even all that similar to chicken and it’s a worse substitute than seitan for something like wings.

The other issue is that big name publishers saw micropayments as eating into their subscription revenue and weren’t interested, but without them it was hard to put together a compelling enough bundle of sites to overcome the signup friction for users.

I still think it’s a good idea but I don’t see how you overcome those obstacles.

Counter to the article, in my experience these are the hardest teams to manage well because organizations typically aren’t set up to deal with them. Larger companies tend to lean into standardization and making things accessible to average engineers in ways that make high performing teams less effective and often demotivated.

I think this is an overly cynical approach that assumes that you can’t invest and grow people into exceptional engineers. In my experience you can if you are willing to invest in it, and the long term benefit of having more high performing engineers who aren’t being restricted from doing good work outweighs the cost of training and growing people.

Apple TV+ doesn’t have an ad-free tier. They have a tier they call ad-free where they still force you into pre-roll ads for apple products. Unfortunately that’s the same for most streaming services that claim to be ad free.