I have a Birdweather puck (https://birdweather.com) that listens for birds in our backyard in suburban Boston. It also measures sound pressure level (30 second sample rate).
Our puck showed a 90.8dB sound level compared to a 55dB baseline.
We thought a tree had hit the house because of the double boom. That was a repeated observation across all the local social media groups. The local UPS driver, who was outside at the time, said he "felt it in his chest".
Interesting this also happened in South Carolina and Ohio within the past few months.
Create a skill that has the CLI in the scripts sub-directory. The implementation language depends on the LLM and the VM it uses. Claude includes shell, python, and a bunch of other interpreters in a Linux environment.
A skill's instructions can direct the LLM to call the CLI.
Claude skills can be installed into Claude web from a web browser. Those skills can then run on the Claude app on your phone.
As the article says, legal action up to this point has been based on the fact that the government created policies that didn't follow its own rules under, for example, the Administrative Procedures Act.
So now the administration is attempting to follow those rules to create these new procedures, which they believe will then be lawful.
If they are successful, challenges would have to be made judicially based on non-procedural grounds, or through Congress.
Early LLMs typically tried to do multiplication "in their head" by recall.
Now most LLMs do multiplication using a tool call to a programming language, akin to a person reaching for a calculator rather than relying on a learned table or working the problem out mentally.
The high level comparison between what LLMs do and what humans do" for this example is fairly parallel.
Claude Code and similar agents help me execute experiments, prototypes and full designs based on ideas that I have been refining in my head for years, but never had the time or resources to implement.
They also help get me past design paralysis driven by overthinking.
Perhaps the difference between acceleration and slop is the experience to know what to keep, what to throw away, and what to keep refining.
On the other hand, LLMs are trained on enormous collections of human-authored documents, many that look like "how to" documents. Perhaps the current generation of LLMs are naturally wired for skill-like human language instructions.
Skills are not just documentation. They include computability (programs/scripts), data (assets), and the documentation (resources) to use everything effectively.
Programs and data are the basis of deterministic results that are accessible to the llm.
Embedding an sqlite database with interesting information (bus schedules, dietary info, or a thousand other things) and a python program run by the skill can access it.
For Claude at least, it does it in a VM and can be used from your phone.
Sure, skills are more convention than a standard right now. Skills lack versioning, distribution, updates, unique naming, selective network access. But they are incredibly useful and accessible.
Skills are not just markdown files. They are markdown files combined with code and data, which only work universally when you have a general purpose cloud-based code execution environment.
Out of the box Claude skills can call python scripts that load modules from Pypi or even GitHub, potentially ones that include data like sqlite files or parquet tables.
Not just in Claude Code. Anywhere, including the mobile app.
I have found that scripts, and the environment that runs them, are the skills' superpower.
Computability (scripts) means being able build documents, access remote data, retrieve data from packaged databases and a bunch of other fundamentally useful things, not just "code things". Computability makes up for many of the LLM's weaknesses and gives it autonomy to perform tasks independently.
On top of that, we can provide the documentation and examples in the skill that help the LLM execute computability effectively.
And if the LLM gets hung up on something while executing the skill, we can ask it why and then have it write better documentation or examples for a new skill version. So skills can self-improve.
It's still so early. We need better packaging, distribution, version control, sharing, composability.
But there's definitely something simple, elegant, and effective here.
Here is a reference to the "Reinventing Government" effort that was implemented during the Clinton administration and considered highly successful (and legal):
But it also expands the idea that the customer/buyer has financial power over the server by encouraging a tipping culture.
Donald Trump and his sons have repeatedly said that don't pay on contracts when they view the work is poorly done or insufficient, in response to claims of non-payment.
Encouraging tipping makes such "payment discretion" easier.
This format requires temporal validity with `valid_from`, but doesn't include `valid_to`. I don't understand how `valid_from` and the also required `recorded_at` interact.
It seems there is no way for a high school student to use Claude for any purpose, including as part of a supervised project or class.