It’s more likely that the person doesn’t like Musk, and unless he’s solving world hunger they aren’t going to be happy. There’s a lot of legitimate reasons to not like Elon Musk, but “not helping the bees enough” isn’t a great take
That’s 150 out of 472 for those curious— thanks for sharing details about access-a-ride, honestly seems like the right solution, at least until 2055 when supposedly 95% will be accessible.
Please consider communicating it more like that rather than putting the focus on the process of the creation. This saves you some irritation by people like me who find it weird and unproductive to do the latter.
Additionally, the author claims to not have vibe coded the features, so some of your credibility is on the line here in claiming they did.
Sometimes, certain processes strongly predict bad outcomes, though.
If someone told me to choose between two barbecue restaurants, where one used an wood-fired smoker and the other used a microwave, my reaction wouldn't be "you really shouldn't judge based on just the process." The microwave is a sufficient indicator of low quality.
Vibecoding (as distinct from using AI as a resource while writing better code yourself) is the microwave: fast, hands-off, low-effort, low-quality.
Do you use coding agents? Just curious bc from my experience using coding agents, open ai’s codex is neck and neck with anthropic’s claude code if not ahead. I wouldn’t agree that OpenAI hasn’t done anything since ChatGPT since codex is my daily driver for software engineering
It's kinda nuts to me how people can act like Claude is lightyears ahead of OpenAI models. Sure, it's one thing to simply have a preference or claim that Claude does some things better, but in reality they are both about as effective at doing the same job. I've long preferred GPT models because they know better how to shut up and don't seem to overthink as much as Claude, but I'm under no illusions that if OpenAI went belly-up then I couldn't do my job essentially the same with Claude. GPT models have also clearly improved over time in terms of programming. There haven't been any "big bangs" necessarily, but it's really not hard to give the same task to 5.3 and 6 and see which one has better output.
That sounds more like semantic search and vector db.
RAG is simply fetching external data (retrieval) and adding it to LLM context (augmenting) prior to generating a final response.
Any time LLMs do a grep or a web search to answer the query, it’s RAG. Many people use vector db for their own RAG implementation bc of the semantic search benefits.
Because people writing about RAG never explained what RAG is and exclusively wrote about embeddings and vector dbs, for most people RAG became "embeddings + vector db".
People don't understand that any sort of retrieval before generation is RAG.
I agree- I also dont think OS features of the kind that get shipped in these updates are convincing anyone to switch from pc to mac or upgrade their mac sooner. Tons of stuff just changing for the sake of change. Meanwhile LLMs increasingly only need the command line to do everything.
I think the truth is most printed copies of books are rarely read even once, so the idea of preserving them is noble but realistically not that important. And may be outweighed by benefits accrued to the person currently owning and reading it making the most of it and marking to their hearts content.
I admit I don’t mark up my books but I feel tempted to try
reply