Have you forgotten Musk nearly sabotaging their own company with tweets tanking their stocks?

I want a client that is simple but flexible by default, extensible, themeable would be nice, and for the love of god has key shortcuts for everything THAT CAN BE CHANGED. LOOKING AT YOU, THUNDERBIRD.

Thunderbird is almost usable for me, but the UI is just absolutely abysmal. The kicker is not being able to change key shortcuts, making Thunderbird unusable for me.

I've never seen something in other well known psychedelics to compare to the health issues I've seen associated with ibogaine, so who is benefitting from us putting all this attention on it now?

I was previously using Steam Connect to do it, but the connection would randomly drop out after a while or suddenly crash the game, so I had to stop doing that.

If I take the Bitter Lesson into account, I would frame this as needing more focus on enabling a general intelligence to use tools more effectively and when appropriate to essentially stop making mistakes.

A basic example being a calculator. The AI needs to recognize its default thinking pattern doesn't work well for math calculations, so it delegates it to the available calculator tool / skill / MCP instead. An LLM should not be relying on LLM prediction to give a mathematical resultant figure, ever. It should come from a deterministic tool. If anything, the LLM may interpret the problem and convert it into starting math figures to use for calculation.

If we can enable AI systems to learn and apply that for themselves, and even develop their own deterministic tooling and sense of what tool to use for what job, that starts to sound promising to me.

Skills feel like a conceptual stepping stone to the next useful abstraction.

Still, it can be dreadful to face even small issues when you only feel like using your computer and not fixing it. Having an LLM agent help with fixing issues is a lifesaver. Ask it what you don't understand, take note of the commands it uses or suggests while troubleshooting and fixing your issue, and you'll supercharge your learning and not get as hung up on the issues.

If someone doesn't care much to learn though, I'd say Linux is still tough to recommend.

When I see how LLMs are capable of essentially prompt and context engineering for themselves, it makes me think they won't need human guidance forever.

When it comes to simple fact-based tasks that have a concrete methodology, it is no surprise to me that LLMs aren't the right tool, and I believe it's a failure of the harness to not recognize those types of tasks and handle them with a more concretely functioning tool instead of relying on statistical probabilities in the LLM "brain" to spit out the correct number to a math problem.

In the same sense that LLMs can use "skills" when necessary, it should have tools or possibly even specialized "brains" for it to pass of certain types of tasks to.

I'm starting to feel that our first form of AGI is not going to be a single brain but an elaborate system of harnesses, multiple LLM models, skills, domain and task specialized subsystems it passes tasks off to, etc. Whether we get there with current LLM technology before some other evolution in AI is the question, to me.

Minimum 1 year of jail time for grossly wrongful arrests that could be avoided with standard procedure or investigation tactics that were not applied.

I'd like to know if my methods are effective. I'm certain they are at least to some extent.

I only ever see research being done about naive and "unskilled" prompting methods. Obviously that's the average user, but just because LLMs are doing poorly in a certain scenario doesn't mean the LLM couldn't excel in the scenario with better direction and prompting. So while it's useful research to be doing, it's a little annoying to only see focus on these examples of "look at how LLMs are bad or biased at this specific thing when prompted in the most straightforward naive way"