561–570 of 786 posts
Earlier quoted context omitted.
I had an encounter with the opposite problem the other day, PM asked me if the library I was using for randomization was "secure" and I said, "Yes, I used the standard Java library for cryptographically secure random numbers that is already used in several other locations in this project," and he said, "But did you ask Claude if it's secure? It has to be secure!"
"Is Claude secure?"
Earlier quoted context omitted.
He's basically asking other people to do his job for him, because he knows that the AI doesn't truly do it well enough. I would say to him that if he wants me to do his job, he needs to pay me his salary.
My VP boss calls me 6 times a day to help him understand his copilot responses and asks why we aren't doing what copilot says we should do. I then have to spend multiple hours explaining why. His peers call him to understand their copilot responses which he then copilots and calls me to help interpret. On and on and on
One way to prevent obvious AI language from sneaking in text destined for other human beings is to ask the model to produce ASD-STE100 Simplified Technical English bullet points. This will result in a list of sentences that are clear and explanatory, easier to double-check, and convenient for the user to rewrite into a more readable format with a human voice.
I deal with this all day long at work and it’s exhausting. People almost acting like no one has thought of it “I asked Claude what happened, and it spit out this 300 line response. Can you read it for me and see if it’s right?” What kills me is you might expect this from a busy high level manager that doesn’t really understand the technical details and they just point the AI to an error they got. They don’t know how…
Deciphering error messages can be a bit of an arcane art, at times impenetrable to all except the authors of a system. Understanding the patterns exposed in such messages and, thereby, deriving their meaning is not always clear even to experienced developers.
Engineers reaching out to you (humans) to explain the output of an LLM haven't fully internalized how to interact with LLMs. When an LLM's output is beyond one's immediate grasp, one can _ask the LLM_ to further break down its output, to explain the concepts and symbols that inform its response.
Personally, I have asked LLMs to draw charts and comprehensively simplify their output, often providing cognitive signposts that "I'm confused" about some aspect of what its reporting.
In other words, some people, including engineers with various lavels of experience, don't yet fully understand the implications of the open-eneded interface that language provides with LLM interaction.
I deal with this all day long at work and it’s exhausting. People almost acting like no one has thought of it “I asked Claude what happened, and it spit out this 300 line response. Can you read it for me and see if it’s right?” What kills me is you might expect this from a busy high level manager that doesn’t really understand the technical details and they just point the AI to an error they got. They don’t know how…
At my dayjob there is a person spearheading ai across the enterprise. They generated lots of documentation across the whole stack and now makes all PO/BAs read it if it's correct. So not just 300 lines - he unironically generated thousands of lines of "documentation" and is now making hundreds of people review it for him Complete brainrot Au psychosis is getting seriously outrageous at this point Thankfully I'm a dev…
Any resistance to this is met with a "But I'm also using AI as the board demands!"
> "frequently contains all too plausible nonsense" This really isn’t the case with frontier models in 2026. I’ve found (sadly) that every time I thought the model was hallucinating, I was in fact the one who was mistaken.
No?
Then, in the document where it writes who has to do what change, it is hallucinating. And this time you or me are not the ones who are mistaken.
Earlier quoted context omitted.
No, it was a suitably nasty reply to someone who boasted of being nasty to colleagues trying to help. If your question can be answered by Claude, and you didn't ask Claude yourself, and when other people do it for you, you complain that you could have done it yourself, then my honest reply is that you should just shut up and learn to use Claude.
Every question can be answered by Claude. Not every question can be answered accurately by Claude. When Claude answers inaccurately, it doesn't tell you that it's doing so, so every answer must be considered "maybe inaccurate". In business, a lot of the time, accuracy matters. If you want an accurate answer, and there's a human who knows, don't ask Claude .
You are assuming that people that send you a Claude answer would send you any Claude answer. This is your assumption- basically a negative prejudice towards those who use LLMs- and has nothing to do with sending a Claude answer per se. Do you understand the difference?
> NATS control-plane events: stream leader election / R3 quorum re-form during pod churn. Whats is wrong with this? I work with durable tracing (not using NATS, or k8s though) and this looks almost exactly what I would expect to see in a coordinator log after repartition of a storage cluster. Obviously I don't know what your actual context was, though.