tobyhinloopen

I have a tool wrapper that captures the output of anything and allows the LLM to query it later, to save on tokens. It “smartly” truncates the output (basically like Node’s util.inspect) and allows the LLM to expand truncated content.

It basically is called like “capture some-cli” and it… captures the CLI output, outputting a subset of it + a handle to continue querying.

This for me solves the danger of a tool returning tons of content.

I failed horribly and might as well used a random coin toss

There was a farm nearby where a mother cat died and all but two kittens died from hunger afterwards. We adopted one, my wife fed the kitten (which was way underage for adopting) with bottle.

Now she has been with us for years. She’s very loyal to me, dismissive to aggressive to anyone else. Not sure why me and not my wife, but hey :)

She basically sleeps next to me all the time, both when I work from home or at night. She’s 14 now, no medical issues.

My main coon is over 10kg and is basically harmless

Oooh so that is why it started doing that! I was so confused how it suddenly started writing that everywhere again

That’s a lot of money and effort for a fake photo

Well, so you can base84 encode your filenames for example. (Jk)

My main concern is the loose matching that comes with it where you can refer to any file or folder using any case without issue

And don’t you dare changing it unless you like random bugs

Tnx!

No demo?

Worktrees or sandboxes. You can tell Claude to put its stuff in a worktree. I can easily develop any amount of features in the same codebase because they all run in their own worktree

You can have a camera doorbell using your copper wire.

With a video doorbell you can get notifications when a person enters your property. You can notify police or neighbors if it’s a stranger

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.