Really regretting chewing on all of those straws as a kid, eating hot food out of all of those takeout trays, keeping my car windows open, living near roads… and…
Since we are doing whataboutism, let's also bring up the ~$1 trillion PPP program, ripe with fraud, enabled and designed by Donald Trump, which helped kick off the current wave of inflation.
>The cost per job saved for one year was $169,000 to $258,000, which was much higher than the average amount—$58,200—paid in wages and benefits to small-business employees in 2020. [1]
It isn't like you can't write tests or reason about the code, iterate on it manually, just because it is generated. You can also give examples of idioms or patterns you would like to follow. It isn't perfect, and I agree that writing code is the best way to build a mental model, but writing code doesn't guarantee intuition either. I have written spaghetti that I could not hope to explain many times, especially when exploring or working in a domain that I am unfamiliar with.
I described how I liked doing ping-pong pairing TDD with Cursor elsewhere. One of the benefits of that approach is that I write at least half the implementation and tests and review every single line. That means that there is always code that follows the patterns I want and it's right there for the LLM to see and base its work on.
Continue and Cline work with local models (e.g. via Ollama) and have good UX for including different kinds of context. Cursor uses remote models, but provides similar functionality.
I may have misunderstood, but it seems the OPs intent was to get the benefits of RAG, which Cline enables, since it performs what I would consider RAG under the hood.
The title reads awkwardly to a native English speaker. A search of the PDF for "latency" returns one result, discussing how naive RAG can result in latency. What are the latency impacts and other trade-offs to achieve the claimed "[improved] answer accuracy by 21.99%"? Is there any way that I could replicate these results without having to write my own implementation?
Back in the late 2010s, I worked with someone who had a personal relationship with PD, to the point that my business partner was soft pitching our business to PD...
The person that I worked with partied with PD and mirrored some of the same (alleged) sort of toxic and abusive antics in their own home and social circles, which I experienced firsthand. There was a darkness emanating from this person that I haven’t really felt before or since. We ultimately stopped working together due to them violating our contract.
The public allegations so far totally jibe with my experience associating with PDs associates and my limited visibility into the world of PD. I’m very glad to have come to my senses and avoided any closer orbit of this world.
That darkness… wow. I’ve met someone like that, and it made me think I was crazy. I guess it’s your brain stem warning you that this person is dangerous in a certain kind of way— extreme dark triad traits.
I have yet to have anything catastrophic happen with pretty liberal usage of YOLO mode in Cursor with pretty weak “safe” instruction guardrails. Then again, I am working with dev credentials on non-critical projects, typically. It does seem like it’s a matter of time until I get prompt injected and divulge some secrets or an over-eager Claude `rm rf`’s /.
reply