- thefourthchimeI completely agree. I can't even imagine using a local model when I can barely tolerate a model one tick behind SOTA for coding.
- I've used all of these tools and for me Cursor works just as well but has tabs, easy ways to abort or edit prompts, great visual diff, etc...
Someone sell me on how Claude Code, I just don't get it.
- My father, who never did any public speaking, and as much an introvert as you'll find, did this for my wedding rehearsal.
I was amazed at how naturally and well he did. All he wrote down were 6-7 topics to talk about. He got a huge applause.
- This is exactly how I write code. I never engineer anything until I have to. I don't try to get rid of code duplication until it works. And I try to be as "least clever" as possible.
- I've worked on a playout system for broadcast television. The software has to run for years at a time and not have any leaks, We need to send out one frame of television exactly on time, every time.
It is "C++", but we also follow the same standards. Static memory allocation, no exceptions, no recursion. We don't use templates. We barely use inheritance. It's more like C with classes.
- My test of a new model is always:
"Generate a Pac-Man game in a single HTML page." -- I've never had a model been able to have a complete working game until a couple weeks ago.
Sonnet Opus 4.5 in Cursor was able to make a fully working game (I'll admit letting cursor be an agent on this is a little bit cheating). Gemini 3 Pro also succeeded, but it's not quite as good because the ghosts seem to be stuck in their jail. Otherwise, it does appear complete.
- Isn't that what GPT 4.5 was?
- The price of inference has been dropping like a rock. I wouldn't expect that 2c to be true in a couple of years.
- As a serial DIYer, I respect the engineering depth here, especially the custom vector index, but I disagree on the self-hosted ML approach. The innovation in embeddings is just too fast to keep up with locally without constant refactoring. You can actually see the trade-off in the "girl drinking water" example where one result is a clear hallucination.
- The article glides over the fact that FMVSS 226 is a performance standard, not a materials mandate. Manufacturers can stick with tempered glass if they beef up the side curtain airbags enough to prevent ejection, which is exactly what happens on a lot of base models and rear windows to keep BOM costs down. The list of brands using laminated glass is accurate, but it applies mostly to their premium trims or front rows only.
There is also the issue of fleet turnover. With the average age of US vehicles pushing 13 years, the install base is still overwhelmingly tempered glass. Writing off the tool entirely because new luxury cars have moved on ignores the reality of what people are actually driving. You are statistically much more likely to be trapped in a 2012 Civic than a 2025 S-Class.
- I like to ask "Make a pacman game in a single html page". No model has ever gotten a decent game in one shot. My attempt with Gemini3 was no better than 2.5.
- About a year
- In a sense, they already do, since they're heavily invested in CoreWeave. For those unfamiliar, CoreWeave was a crypto company that pivoted to building out data centers.
- I wonder if the senior dev actually said LLM, or at least meant LLM. If he said that, most of this checks out. The only thing is that they don't have to be stochastic, but in practice they almost always are.
- I've been at companies as small as 10 and as large as 30,000. and there is no lack of politics in smaller companies from what I've seen.
- Or, they do know and don't want to say. This project does seem to have funding so I assume there is a plan.
- Can you answer question 7?
- Huh, checks out. Interesting!
- You must not watch broadcast television (e.g American Football). Anthropic is doing a huge ad blitz, trying to get end customers to use their chatbot.
- Yeah, true. I worked for a big tech company when they were building a team in China so they could lay us all off in Palo Alto.