SkyPuncher

VSCode for the rare time I need to view a file.

GitHub or Tuicr for code review. Still waiting for an agentic first review environment- which Jetbrains has missed the ball on.

I have paid out of pocket for Jetbrains for 15 years. I don’t think I’ve opened it in the past year and should probably cancel my subscription.

For me, the things that made Jebteains great just don’t matter anymore.

I do security review for my company. I suspect this is a means of containing OAuth redirect vulnerabilities. We basically needed to do the same thing with our MCP server.

The security problem is two fold: (1) companies want control over where their data goes. Figma allowing any MCP creates problems (2) open redirects can create phishing issues. If your using Pi, you’re probably thinking of this. Most users aren’t.

For us, we decided to do an allowlist pattern because it was a reasonable tradeoff. The solution is allowing per-tenant client configuration, but that comes with its own set of issues (dev time, support, maintenance, etc). When nearly all of the money is flowing through a handful of well-known MCPs there’s little reason to out effort into supporting every MCP.

I have never heard of this. Do you mind sharing some examples?

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.

* Only, then can I review it and send it it.

Said MCP server (missing the actual ops): https://github.com/clops-mcp/clops-mcp

It’s terrible.

I’ve always wanted it to be better, but it’s just terrible. It’s like working on a projector screen where the pixels never line up.

Anyone know the resolution?

I have Xreal airs. And, while, I like them, they’re rather useless because 1080p just isn’t enough.

These work best on a targeted section of the code, like a PR.

“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.

You don't need any real legal basis. We're talking about kids sporting events. Social pressure is often enough.

You don't want to be the reason your kids team lost. You don't want your kid getting kicked of their team for your behavior.

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.

For me, the hardest part is actually figuring out what the cable is called in order to find a replacement.

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.

For me, no. I’ve started tracking session ID on every ticket I work on in order to be able to find them again.

Having it in the commit message is handy (not to mentioned I already have it I. The commit message).

I’ve never been under the impression that privacy relay is anything like a true VPN. I mostly thought it stopped BS that happens on public WiFi and public sniffing. It’s meant to protect you only until you get to a major carriers infrastructure.

I get tripped up on the intensity of its us and the ambiguity it tends to apply them with.

Minor inconvenience != load bearing, yet Claude consistently uses it while missing actual loading bearing things.

Likewise, it tends to jump to terminology that’s technically correct but practically meaningless.

Working in startups has left me with almost the opposite problem. While there are many theoretical problems to solve, most are not valuable to solve until you have a reasonable degree of confidence that customers care about them.

Yea, I don’t have any interest in trying Fable because I’m not interested in the BS that’s going to come with it.

I’m at the point where I need stability and predictability. I want the B- student who shows up everyday rather than the A+ student that’s unreliable.

I went down this rabbit hole earlier in the year.

You generally don’t need error correction. Instead, you do a retraining of sorts where you basically fine tune the model on the target chip architecture. Because these systems are so complex, errors tend to localize without affecting overall output.

My understanding is the hardest part is actually noise in the analog system.

I’ve generally come to this opinion as well. The only thing I would seriously consider auxiliary power for is the furnace.

Winter storms tend to come in cold stretch’s that can cause major freeze havoc.

In this case, I actually view it differently than just a diplomatic position.

Ideally, these teams have processes and standards that they use to enable other teams.

If someone says “I have this cool new food product”, regulatory teams say “Amazing, here’s how we can help bring that to market.”

This was my high school experience and many people I knew.

* School at 7am

* Sports practice after school. Game days were basically all night events.

* might take an hour or two break

* 2 to 3 hours of homework

For junior and senior year, I worked 16 hours on the weekends as well.

I don’t view that team as saying “No”.

Instead, I view that team as saying “Customers expect safe food. Our job is to help you deliver on that”.

I realize this like a decade ago. Security is basically the only thing I care about in code review.

I’ve come to realize that I don’t actually care what your code looks like. I’m going to need to learn it from scratch every time I use it. It’s going to look weird and foreign to me no matter what. It’s not worth my time nit-picking things that simply do not matter.

Hmm, I guess I haven’t notice the sour flavor. Con-Crete is the brand I use and the flavors are naturally sour.

Monihydrate causes me terrible GI issues and insomnia. I’ve found HCL to me much easier on my body.

ADHD is unlikely to be the root cause as there is unlikely to be any single root cause. Treating ADHD will reduce or eliminate a component of this, but will not address the issues entirely.

This makes sense to me as a correlation. Mental health disorders alone seem like they’d contribute significantly.

ADHD, for example, is correlated with both sleep cycle issues and worse outcomes in life (including higher rates of crime and participation in risky activities).

I think we’re seeing a similar thing pan out with AI. When the barrier for something is too low, people realize that it’s not actually worth the other party’s effort to communicate it to them.

For me, physical communication is quickly becoming a signal that someone actually put effort into things.