1,392 karma · joined January 24, 2016
To be effective in using low level languages, LLMs would have to build higher level constructs like subroutines from scratch every program.
It's not that different from why we almost never use assembler for anything more than code islands: even a modest subroutine can overwhelm our own mental context window.
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.
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.
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.
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.
Claude on the web does this. The only issue is controlling network access, which could be fixed by per-skill ACLs.
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.
* references/ Contains additional documentation that agents can read when needed
* scripts/ Contains executable code that agents can run.
* assets/ Contains static resources
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.
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.
Not only do many VR and AR systems acquire stereo, we have historical collections of stereo views in many libraries and museums.
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.
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.
https://en.m.wikipedia.org/wiki/National_Partnership_for_Rei...
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.
For instance, it tells the possibly apocryphal story of how the telephone allowed male suitors to call reach young women directly and thereby bypass both protective parents and long-time traditional romantic competitors. Getting a phone call was so exceptional that people had not yet built up any social defenses for it.
https://github.com/slavingia/va/blob/main/eos/analyze_eos.py
System prompt:
You are an AI assistant that analyzes internal government memos for compliance with 2025 Executive Orders. You identify references to DEI, gender identity, COVID policies, climate initiatives, and WHO partnerships that must be removed or modified according to new directives. Provide detailed analysis and be precise about what needs to be changed."
Based on this memo analysis, provide a detailed assessment of non-compliance with 2025 Executive Orders:
MEMO CONTENT:
{text[:10000]}
Rules for determining non-compliance:
1. DEI/DEIA Content:
- References to "diversity", "equity", "inclusion" in policy context
- Mentions of equity action plans
- References to Chief Diversity Officers or similar roles
- Performance criteria based on DEI targets
2. Gender Identity Content:
- References to gender identity or preferred pronouns
- Content about gender ideology or training
- Instructions to use non-binary pronouns
3. COVID Policy/Telework:
- COVID-19 vaccination requirements
- Pandemic-era remote work extensions
- Masking or testing policies that remain in effect
4. Climate/Environmental Content:
- References to climate resilience, zero-emission requirements
- Environmental justice language
- Sustainability criteria in purchasing/contracting
- Plastic straw bans or similar procurement restrictions
5. WHO Partnerships:
- References to World Health Organization partnerships
- Alignment with WHO protocols or frameworks
6. Other Key Areas:
- Affirmative action or racial/gender preferences in contracting
- $15 federal contractor minimum wage references
- Student loan forgiveness expansions
- Paper check disbursement references
Perhaps not coincidentally, that's what efficient (or "lazy", you choose) developers do as well.
Running commands one by one and getting permission may sound tedious. But for me, it maps closely to what I do as a developer: check out a repository, read its documentation, look at the code, create a branch, make a set of changes, write a test, test, iterate, check in.
Each of those steps is done with LLM superpowers: the right git commands, rapid review of codebase and documentation, language specific code changes, good test methodology, etc.
And if any of those steps go off the rails, you can provide guidance or revert (if you are careful).
It isn't perfect by any means. CC needs guidance. But it is, for me, so much better than auto-complete style systems that try to guess what I am going to code. Frankly, that really annoys me, especially once you've seen a different model of interaction.
Dooring remains one of the greatest threats to bicyclist safety in many locations. Even places with great bike infrastructure often have streets with parking where cyclists must ride.
Any plans to include diffractive optics as well? (A totally self-serving question, given that refractive optics is much more common.) In a past life I taught holography and wrote interactive programs to visualize the image forming properties of holograms.
I was able to internationalize it for 45 major languages across the world (still subject to human testing). That allows it to be accessible for 85-90% of the world's population.
It cost me about $50. It saved me months of work on a "labor of love" project and allowed me to add lots of quality of life features in a single day that I just never would have gotten to otherwise.
That's an enormous value for me.
These changes also directly impact research hospitals, not just universities.
That doesn't mean indirect costs shouldn't be reformed. This is just simply the most disruptive possible way to do it.
The FAA Academy where all flight controllers are trained is way over-subscribed. Recruiting policies aside, I can find no evidence that the FAA wasn't training as many controllers as it could through its academy. This fact remained true through the Trump 1 administration into the Biden admin, except for COVID. The pandemic was understandably a huge disruption, as were government shutdowns.
We can know this from the FAA Controller Staffing reports from 2019 (Trump 1 before the pandemic but after Obama) and 2024 (Biden). The 2024 report has been scrubbed from the FAA website when I last checked, but is available through the wayback machine:
2019: https://www.faa.gov/air_traffic/publications/controller_staf...
2024: https://web.archive.org/web/20241225184848/https://www.faa.g...
There appears to be no urgency in Trump 1 about this issue in the report. Things changed in 2023 when an external safety report revealed the staffing problem and suggested improvements.
https://www.faa.gov/NAS_safety_review_team_report.pdf
As a result, hiring almost doubled between 2010 and 2024, with 1800 controllers hired in the last year. More importantly, the FAA followed the report recommendation to use CTI schools as additional academies:
https://www.govexec.com/workforce/2024/10/amid-hiring-surge-...
It seems like the Biden administration took real action to address a problem that had been unfortunately present and unacknowledged for many years.
See a chatgpt analysis comparing the two reports here: https://chatgpt.com/share/679eb87f-c4fc-800a-a883-3b7f79e06d...