Plan mode was great, but I realized I progressed well beyond it. I found that I was getting these categories repeated errors and oversights from Claude (and frankly it hasn't gotten much better about this). Skills were too generic and got lost to context.
I ended up building out tool an MCP server that I use as a bit of a psuedo harness for Claude. I have a variety of multi-step workflows that are basically micro-skills stacked on top of each other. This helps me make sure that I can get Claude to think in a repeatable and reliable manner.
For coding, I've found that I have a few specific steps that Claude needs to do before I'm comfortable letting it loose:
* It must extensively explore the code base (including certain areas that it misses)
* It must think about what it doesn't know or is making assumptions about
* It MUST scaffold out it's intentions. Essentially, it can write comments, classes, and method stubs - but no actual content. Very much like a spec, but since it's in and alongside other code, it's much easier to identify problems.
* It must spike and validate key assumptions. This, plus the prior step, are the only way I've figured out how to avoid it ending up in a confusion loop. Too often it looks at poor-quality code it's written and thinks it's a long-term solution. By avoiding writing code as much as possible, it knows that it's draft content.
Really? Did you ever try adjusting the text sharpness?
I've a pair of Nreal Air glasses (before the rebrand) and a pair of Xreal Ones. I have found the latter remarkably comfortable and sharp enough for coding, reading text, playing games, etc. for extended periods of time.
The new widescreen modes are a real treat too. Still waiting for Real 3D to get upgraded to 60FPS though.
2412 x 2288 per eye (and horizontal FoV is around 70 degrees). Not sure it's really enough for monitor replacement, but certainly an upgrade over Xreal's offerings.
“I haven’t brushed my teeth, but I don’t have a cavity - so I’m good”.
Don’t get me wrong, my “fun” car (an old, beat up Jeep) is going on 2 years with the same oil (I barely drive it), but I known I need to change it soon.
Oil degrade with oxygen. Every time you drive that car, the oil are being re-oxygenated and continuing to degrade (along with being exposed to combustion byproducts).
Also, the type of wear you get often isn’t noticeable until it becomes catastrophic. In my case, a 30 year old car that’s already on its last legs “catastrophic” is more like “time to finally drag it to the scrap yard”.
Engine oil is pretty much the only critical one because of the tolerances between the piston and the cylinder. Loose tolerances allow bypass (inefficiency), but tight tolerances require good lubrication (friction). Engine oil is also unique because it’s exposed to oxygen and combustion byproducts.
The other components just aren't as sensitive or exposed to as much abuse. Often, really only needing replacement if they’ve leaked out.
I remember a parent being "ejected" when I was younger. Technically, they didn't "have to leave", but social pressure is enough for them to recognize they should leave the situation.
* All of the parents already know who the abusive parent is
* The first warning was the coach talking to the "entire group" (at a natural stopping point). The group dialed it back (there will always be some controversial calls), but that one parent didn't get the message.
* Finally, the game stopped suddenly (ball was in play, but in a neutral position) and they we're directly addressed by the ref.
This caught the abusers attention. This was an abnormal event. They were being addressed directly. Whether they realized they were the problem, they certainly recognized the social pressure. They recognized how embarrassing it was (sadly, they probably didn't realize how embarrassing it was for their kid) and decided to take the ref's suggestion to cool down.
I feel like I feel this increasingly as I age. I used to be able to remember nuanced details of API and computer systems. Now, so many of those memories simply get stored as “FLAG: double check the docs” (because I’ll forget).
I’m a lot better at assessing things from a high level, knowing where to find the information I need, and knowing how to assess it for accuracy - but I can’t remember details anymore. Books become summaries. Trips become a few key snapshots representing the trip.
I ended up building out tool an MCP server that I use as a bit of a psuedo harness for Claude. I have a variety of multi-step workflows that are basically micro-skills stacked on top of each other. This helps me make sure that I can get Claude to think in a repeatable and reliable manner.
For coding, I've found that I have a few specific steps that Claude needs to do before I'm comfortable letting it loose:
* It must extensively explore the code base (including certain areas that it misses)
* It must think about what it doesn't know or is making assumptions about
* It MUST scaffold out it's intentions. Essentially, it can write comments, classes, and method stubs - but no actual content. Very much like a spec, but since it's in and alongside other code, it's much easier to identify problems.
* It must spike and validate key assumptions. This, plus the prior step, are the only way I've figured out how to avoid it ending up in a confusion loop. Too often it looks at poor-quality code it's written and thinks it's a long-term solution. By avoiding writing code as much as possible, it knows that it's draft content.
* Only, then can I review it and send it it.
Said MCP server (missing the actual ops): https://github.com/clops-mcp/clops-mcp
reply