lostdog

Maybe it's time to do pair agentic engineering? Have two engineers at the screen, writing the prompts together, and deciding how to verify the results.

Whoosh

In MCP setups you do give the agent the full description of what the tool can do, but I don't see why you couldn't do the same for executables. Something like injecting `tool_exe --agent-usage` into the prompt at startup.

Great article otherwise. I've been wondering why people are so zealous about MCP vs executable tools, and it looks like it's just tradeoffs between implementation differences to me.

Yes, sites should support a NoAds header that agents can provide, which ensures that the site doesn't provide any ads that the agent could accidentally click on.

And get it into a modern certification. Want LEEDS? Get the sound measurement people out.

Please post your address. I'd like to help make your home "feel alive."

They are oppressed by their neighbors, who can scribble all over their home without consequences.

Have you had to clean off graffiti?

We begin teaching math by having students solve problems that are trivial for a calculator.

Though I also wonder what advanced CS classes should look like. If they agent can code nearly anything, what project would challenge student+agent and teach the student how to accomplish CS fundamentals with modern tools.

I wonder if you could calculate a "probability of response to major alert" and make it the inverse of the total or irrelevant alerts. Then you get to ask "our probability of major alert saliency is onlt 6%. Why have the providers set it at this level, and what can we do to raise it?"

Is it ironic that the project with the most potential for making C++ build quickly is suffering the most from C++ being extremely slow to build?

Beyond that, what a superb overview. More open source projects could learn from this posting. It provides a great list of areas for someone who wanted to get started contributing.

Weird. I find Opus knows the answer more often, plus its explanations are much clearer. Opus puts the main point at the top, while Gemini wanders around for a while before telling you what you need.

There's a simpler design here begging to show itself.

We're trying to orchestrate a horde of agents. The workers (polecats?) are the main problem solvers. Now you need a top level agent (mayor) to breakdown the problem and delegate work, and then a merger to resolve conflicts in the resulting code (refinery). Sometimes agents get stuck and need encouragement.

The molecules stuff confused me, but I think they're just "policy docs," checklists to do common tasks.

But this is baby stuff. Only one level of hierarchy? Show me a design for your VP agent and I'll be impressed for real.

The right number of frameworks in a company is log10(number of employees). Go over this limit, and everyone needs to learn too many frameworks with too little support, examples, tools, and documentation.

I also think the author is understating how bad the original framework was. I've seen some of these and the "itchy points" are real true problems. The team supporting the framework decides that fixing the pain won't get them promo because it doesn't show up in any metrics, and certainly they won't accept your submitted improvements. Your only choice is to wrap it.

Of course, since their thing is a framework, your wrapper must be a framework too. (Is it possible to wrap a framework into a library?)

The end of the story is even sadder. You work on your replacement and wrapper, and oh no, the framework you are wrapping has problems or slowness because of the framework it depends upon!

Yes, I've also been confused by things like this. Claude code is sometimes saving plans to ~/.claude/plans under animal names. But it's not really surface where the plan goes, not what the expected way to refer back to them is?

Yup, the "switch desktops/spaces" input lag is the absolute worst on Mac. It's remarkable that Apple has a reputation of being good at UX.

Agreed, I don't love the CLAUDE.md that gets autogenerated. It's too wordy for me to understand and for the model to follow consistently.

I like to write my CLAUDE.md directly, with just a couple paragraphs describing the codebase at a high level, and then I add details as I see the model making mistakes.

This kind of behavior should re-open the return window for the car.

Backblaze stuck my email on a list, and now I get daily marketing spam from them. They shattered that good will with me very quickly.

Then you'd need to pay more doctors, and it would be much harder for the hospital to make a lot of money!

I'm just using "resistance" as a joke here.

But seriously, I am curious how you previously made decisions about who to vote for, and how you are thinking about changing how you decide your voting preferences in the future?

What about building something bigger?

If AI lets you build the basic version immediately, then try adding features until you get stuck. Extend your todo app to have gantt chart scheduling with drag and drop and automatic reflowing. Give your video game more realistic physics. Etc

I take 10k IU of vitamin D if I feel a cold coming on. I used to get extremely bad colds very frequently, and every time I get frustrated and read whatever research might be helpful. A year ago I came across some info about LL-37, and found that vitamin D might help, and that's when I started taking it. https://pmc.ncbi.nlm.nih.gov/articles/PMC9134243/

The big dose of D seems to help. I'm certain I'm deficient, since I already take 2-4k daily, which noticeably helpsy winter blues. It's the first time I can "arrest" a cold, and even if I get sick the symptoms aren't nearly as bad.

My full protocol for if I start feeling a cold is this:

1. 10k vitamin D 2. Stay extremely warm when I sleep. Uncomfortably warm. 3. Butyrate (probably a placebo) 4. Curcumin (almost certainly a placebo).

Yes

> Hi, Trump voter here. I'm NOT fine with this.

Welcome to the resistance!

Just curious. Since you voted for someone who is a terrible President last time, what are you planning to change about how you make voting decisions next time? Are there particular people or media you plan to listen to less, and others more? Particular aspects you will weight higher or lower?

If someone was working to bring elections to North Korea, then they too would deserve a Nobel.

Your source is a press release by the Trump administration?

Is there a source for this or did you just make it up?

Isn't the Nvidia shield the thing they added ads to way after they were sold?

For a self-driving company, replacing a lot of drivers servicing some passengers is much better financially than replacing a few drivers servicing many passengers. Pencil it out yourself and you'll see that doing robotaxis is much better than doing robobuses. Plus, have any cities suggested that they would contract out their business driving to an automous company? Has anyone asked the unions to see what they might do about it?

Autonomous buses will come, but only after the approach has fully taken over the taxi market first.