tobyhinloopen

Don't developers configure their LLM tools to only be able to access things the user using the LLM should have access to?

Gotta love the LP4 mode. So much music on a single disk! Remember the cool rectangular batteries? Why aren't these gumstick batteries more used in modern devices!?

I'll 100% try DuckDB in more serious projects where I would normally use Sqlite.

The only reason I know and use DuckDB is because my (internal, private-use-only, experimental) vibe coded projects use it a ton. I didn't pick it - LLMs did. Until this article, I wasn't aware of what it actually is capable of.

Most of these projects use JSON(L) files for storage, and duckdb to process them.

Try the superpowers plugin, let it write a spec (what do you want?) and a plan (how is it implemented). Then let it implement the plan.

Review each step as much as you care. These things take time so you can just do other stuff while it’s cooking.

With proper isolation of projects you can easily have multiple sessions in parallel. I frequently have 4 to 8 parallel Claude Code sessions, each with whole trees of agents reproducing, speccing, planning, implementing and reviewing things.

For common mistakes, you can make it remember things or rely on reviews.

You know what’s worse (less efficient) at parsing and writing code than LLMs?

Humans.

“This is a significant rewrite that will take weeks”

Done after my potty break

Try it on RAM and CPU.

It’s slower but you can run them.

That’s a great idea. Maybe use Claude Code with some owasp knowledge to sweep through them and see if there’s anything obvious?

Because the air is squished out I suppose

Min Release Age of 7-30 days covers the majority of potential issues with 0 effort.

All major Node package managers should support it by now.

Prom was the best IIRC, yarn second, but even npm is catching up

I agree with this, It feels like a small upgrade like Opus 4.9 or something.

It’s still pretty good though

I’ve been doing pentesting with LLMs for a while and only hit a few “nope I won’t do that” and one “this conversation is flagged for being against the TOS”. No idea what the guardrails are but they are trivially abused

Claude “respond in a friendly way that I agree with this comment”

I actively support “my boss” to run Claude Code. I offered them to help and made jokes it’s so easy these days they might as well just call Claude Code themselves. I’ve shown I could plop in their documents of feedback and Claude fixed the issues.

I have worked with non-tech employees to set up Claude to help them do small tasks. I’ve helped to review and improve completely vibe-coded projects by such employees.

I’m not sure what my role will be, but I fully embrace that my traditional role of writing code is gone.

I told something like “your value lies in reviewing the output yourself before sharing it, not in calling Claude. I can also use Claude.”

You can order LLMs to use other patterns. I had an LLM recreate an app in a different stack with reasonable success

You mean these tools you can now rebuild at the cost of a night and one Claude code subscription?

You have to have an ordinarily unique startup if your software can’t be recreated quickly.

That’s a bold claim to randomly write without any supporting sources

Just as long as you speak a major language

(A) I spent day and night using and making tools with and for LLMs. (B) As much as I humanly can.

I think this is the first time I saw someone describe so clearly my concerns and experience with LLMs.

I have little to add to it, except that I agree completely. Not sure what’s next

I expected a “running for beginners” app hah, like for training / endurance

Not sure yet. I’m monitoring it.

However, it is totally viable for internal tools, rapid prototyping, experiments, etc.

Frankly, there’s no faster or cheaper way to get such feature rich apps, and it was certainly better then what a cheap agency from far-away would produce.

Not only was the code better, the whole product was better than what I would have made (before coding LLMs), because he understood the domain, and AI filled in many details that I wouldn’t spent time on. (Again, pre-LLM)

I’m just… multiple times a week I’m sitting at my screen like, wtf will I do? What will my job be? I have plenty of time to think about it while Claude basically handles everything I throw at it.

Good thing I spent months learning to apply skills and such so my value is “experience with using LLM tools” (:

It’s interesting though because the client’s dev team basically refused to look at it, dismissing it as insecure and such.

I realized that the software he had made was actually better than what I would have made, because he understood the problem better than I ever will, Because it was his job to understand the problem, not to write code.

It was the first time I realized that AI can totally replace me in my traditional job of trying to understand client’s wants and needs and convert them into an application by writing some code.

I knew Claude was powerful and spent months creating skills prompts etc but this guy did it from scratch.

A non-technical employee of a client vibe-coded an app and I was asked to review and deploy it.

It was okay, not bad at all. No serious issues.

At the same time, me feeding a whole PDF of feedback from a client - screenshots and such - into Claude, and it fixed everything after 7 hours of reproducing and fixing things mostly unattended, creating a bunch of MRs with fixes. Most fixes were good, some were obviously not what the client wanted but technically correct (which I told Claude and it fixed it)

I tried Darktable a few times and I just couldn’t stand it hah. I’ll try it again, hah, Tnx!

I like that it runs on Linux but coming from Lightroom, it is a challenge to use. I don’t even know how to import photos that are added to a previously imported folder

I never had that happen to me, in all the years I owned it. It also doesn’t randomly wake up and throw my ink away, and sometimes it sits weeks unused. It’s in my home office, so I would know if it randomly wakes up.

The only bad thing is that it can get messy if you select the wrong paper type and the ink will not be absorbed by the paper, making the rollers dirty. That’s annoying but fixable, and preventable by not selecting the wrong paper type.

It behaves like slower ram I assume, due to the increased distance from the CPU and overhead. Still, it’s much faster than normal SWAP which uses a disk or SSD.

How it is reported? As SWAP space, not as RAM.