Similar experience here, however my feeling is that this isn't necessarily a bad thing. Garbage being made is indicative of a gap in the currently-available tools. User research should shift towards analyzing these prototypes and enhancing existing tools to fill this need.
This was one of the first ideas me and my team had for sharing skills and scripts. The problem is this is a very "why Dropbox and not FTP" answer.
The second you utter the word git, you may have lost 90% of your audience - depending on their background, of course. MCPs are a lot more non-tech friendly
yeah it 100% depends on who you'll be sharing them with, for me its just myself and a couple agents i have on a dedicated machine so git is ideal to keep versions matching when i update something on my daily driver
My mental model for MCPs is that it's like a Swagger/OpenAPI spec for LLMs. Point 2 doesn't make much sense in that context as it's describing MCP as a Swagger endpoint that's unstable.
Chrome/Ghidra MCP does have a tendency of crashing, but I'm not sure why this is. Is my way of thinking of MCP incorrect? If it really is a descriptor of how to talk to another tool, then why do they seem fragile at times? I feel like there's a gap in my knowledge somewhere.
Of course they do. Generally the end result from this is bad - reduced in scope, buggy, and/or unstable. But that's an issue with communication/expectations/management. It'll keep happening either because of politics or the fact that a sub-par deliverable still meets the needs of the overall organization. Until it doesn't.
From what I understand, that's a problem with the way it receives data. The model doesn't see the letters g,o,o,g,l,e to count it. Just like how I can't sense radio waves. If I wanted to find that out, I'd get a tool to detect waves. If the LLM wants to find that out, it can write a script to find it.
I suppose it depends how hands-off the tasks are - I max out at 2 parallel sessions working on different parts and it's fairly exhausting once done. I can see the number of parallel work increasing if there's a good dev/test loop. But at $WORK, that's not usually an option.
So, hands-off meaning "just let the AI cook and don't check it"?
Either you follow everything it does, revise the plans, do the code review, manual adjustments, etc, or you run sessions in parallel, not being that attentive and constantly context-switch (also resulting in less attention I guess).
AMD and any other corpo is made of people, who do have emotions. Abuse towards these people impacts corp operations. This is an entity protecting itself from damage that it feels is not worth the benefit the offering would bring.
And I question your assertion of real harm to individuals, by not offering free support, being worse than receiving verbal abuse.
Right, but saying "this policy change is disgraceful" and saying "you, customer support person, are an insufferable dickhead" are very different things. From what I can see in the link comments, people seem to be saying mostly the former.
Was the abuse and response directed at a person or AMD? Even AMDs response is vague and deflects it as “Abuse towards AMD”
AMD is free to change their terms of their product, but then characterizing the backlash as abuse towards AMD is laughable. Have empathy for people not corporations
From what I understand, they can get call records and subscription info w/ administrative subpoenas, but this is the first I've heard of them being able to get location data without a warrant.
Assuming you meant directly from the telcos and not from the data broker loopholes - in which case pretty much anyone should be able to do that. Emails and texts they still need a warrant for.
I'm not well versed at reverse engineering binaries or interpreting C/assembly so ghidra MCP has been an absolute gamechanger for helping me write tools. Once my project is complete, I plan to learn how to do the analysis myself manually and have cc guide me along the way.
Putting some numbers into the discussion census.gov [0] is tracking a sharp decline in net immigration due to both, a decrease in immigration and an increase in emmigration, from the start of 2025 to the present. Trending towards a net negative.
Pew [1] suggests that the changes around the start of 2025 were due increased restrictions on asylum applications under the previous admin and EOs by the current one to restrict new immigration. Given the rough numbers [2] of about 40k asylum grants per year in the early 2020s, I doubt the previous admin's actions are playing much of a role here.
Stating that none of it (immigration acceptance) changed under this administration might technically be true - with respect to the number of countries applying, but misses this point.
No doubt some changes were made by both Biden and Trump, but the argument being made is that this was fundamentally xenophobia, which is not supported.
reply