Econolicious

1.5K posts

Econolicious

Econolicious

@econo

Economist, ubiquitous

NYC شامل ہوئے Aralık 2008
846 فالونگ246 فالوورز
Econolicious ری ٹویٹ کیا
Rimsha Bhardwaj
Rimsha Bhardwaj@heyrimsha·
Prompt engineering is dead. Anthropic recently released the real playbook for building AI agents that actually work. It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design. Here’s the big idea: A Skill isn’t just a prompt. It’s a structured system. You package instructions inside a SKILL .md file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat. But the real unlock is something they call progressive disclosure. Instead of dumping everything into context: • A lightweight YAML frontmatter tells Claude when to use the skill • Full instructions load only when relevant • Extra files are accessed only if needed Less context bloat. More precision. They also introduce a powerful analogy: MCP gives Claude the kitchen. Skills give it the recipe. Without skills: users connect tools and don’t know what to do next. With skills: workflows trigger automatically, best practices are embedded, API calls become consistent. They outline 3 major patterns: 1) Document & asset creation 2) Workflow automation 3) MCP enhancement And they emphasize something most builders ignore: testing. Trigger accuracy. Tool call efficiency. Failure rate. Token usage. This isn’t about clever wording. It’s about designing an execution layer on top of LLMs. Skills work across Claude, Claude Code, and the API. Build once, deploy everywhere. The era of “just write a better prompt” is ending. Anthropic just handed everyone a blueprint for turning chat into infrastructure. Download the guide here: resources.anthropic.com/hubfs/The-Comp…
Rimsha Bhardwaj tweet media
English
154
962
7.9K
1.1M
Econolicious ری ٹویٹ کیا
Steven Pinker
Steven Pinker@sapinker·
Emily Oster @profEmilyOster,always fierce with data and gentle with people, offers more wise advice: Ignore advice about the claimed advantages of this or that type of exercise when they are based on correlational studies, & do the kind of exercise you enjoy (and thus will stick with). nytimes.com/2026/02/23/opi…
English
0
16
205
35.3K
Econolicious
Econolicious@econo·
Six months ago, CostcoUSA started widely promoting executive membership for an extra $10/month to gain an exclusive executive-only 30 or 60 minute daily store hours for shopping. Costco knows.
Econolicious tweet media
Hugh Rant@hughs_rants

@Pavel_Asparagus Yesterday, I would have scrolled right by this post. Today, my brother dragged me to Costco to "pick up a few things." Costco -- where abundant crap goes to be pawed at by armies of reincarnated cart-pushing zombies. All I wanted was to a premium to shop alone.

English
1
0
1
52
Econolicious ری ٹویٹ کیا
Dario Amodei
Dario Amodei@DarioAmodei·
It's a companion to Machines of Loving Grace, an essay I wrote over a year ago, which focused on what powerful AI could achieve if we get it right: darioamodei.com/essay/machines…
English
125
216
2.3K
785.7K
Econolicious ری ٹویٹ کیا
Steve McGuire
Steve McGuire@sfmcguire79·
Dartmouth President Sian Beilock: “Assuming that most Americans value our mission is a recipe for irrelevance and decline. We must demonstrate to students and families—and to the broader public—that we’ve heard their criticisms and will address them.” Five steps: 1. “Make college affordable” 2. “Return on investment matters…there must be an undeniable return.” 3. “Re-center higher education on learning rather than political posturing.” 4. “Emphasize equal opportunity, not equal outcomes.” 5. “Testing is important.”
Steve McGuire tweet media
English
131
529
4.4K
1.1M
Econolicious ری ٹویٹ کیا
JLee🟧
JLee🟧@X0_1_7ex·
"This is the modern university in miniature. On the outside: polished, generic optimism. On the inside: exhausted scientists, shrinking trust, and a widening gap between what administrators say and what actually happens." Very powerful, Dr. Locasale. I wonder if they didn't get the idea from the Democrats. For decades Democrats have been more committed to form/PR over substance. It has worked well for them bc the media backs them 💯. It's the same w universities. The media is fully committed to the establishment, and presents it the best light without exception [Christopher Rufo exclued].
English
0
1
1
171
Econolicious ری ٹویٹ کیا
Austin Berg
Austin Berg@Austin__Berg·
Chicago is investigating how residents learned of a meeting to hike their property taxes. It’s a story that reads like The Onion. Chicago Board of Education President Sean Harden called a special meeting over the Christmas holiday. He had one objective: Quietly pass a $25 million property tax hike. But Harden’s plan hit a snag. Fox 32 Chicago political reporter @paschutz published news of the meeting before the school board posted a public notice of its own. And now Harden—with Brandon Johnson’s imprimatur—is spending taxpayer money on a law firm to conduct an investigation into how news of the meeting leaked to a journalist. That’s absurd. But there’s an even bigger scandal here: The school board is subverting democracy. Specifically, Chicagoans should be seeing a referendum vote on an extra $550 million increase in property tax collections that will flow to Chicago Public Schools this year, above what’s allowed under the state’s property tax cap. But Chicagoans will not get that vote. Go deeper in this week’s edition of The Last Ward ⬇️ open.substack.com/pub/thelastwar…
English
54
422
1.5K
65.3K
Econolicious ری ٹویٹ کیا
Econolicious ری ٹویٹ کیا
Dean W. Ball
Dean W. Ball@deanwball·
I received an immense amount of hate for this tweet; this surprised me. But one thing didn’t surprise me: none of that negativity came from people whom I associate with the AI safety or “doomer” communities. On its face, this *should* surprise you. If you had no context—if you were an alien—you would think “AI safety” and certainly “AI doom” people would *hate* the idea of AI being used to transform science, up to and including autonomous experiments. Such things are even in doom scenarios! Yet they do not hate this EO, and many are supportive. This is because they are generally techno-optimists, as I have pointed out for a long time now. Fundamentally, they want the benefits of AI (for the most part; obviously there are exceptions). Instead, the large volume of negativity I saw came from people with a much duller and more ambient anti-tech sentiment. They believe this EO is a “bailout” for “AI oligarchs,” and that AI is entirely fraudulent. Look at the replies; they hold all sorts of asinine slop-beliefs. Soon enough it is possible that ~all AI discourse on this site will look much more like this than what it has looked like for the past two years. I hope not. But either way, the safetyists and the accelerationists—at least the intellectually honest among them—will soon realize that they are much closer on the spectrum of opinions about AI than they ever thought possible. (N.B.: It’s very plausible lots of these accounts are bots working on behalf of anti-tech economic interests or foreign governments (all successful misinfo campaigns are based on things people already “want” to believe), but at least some of them are not.)
Dean W. Ball@deanwball

Very excited to see this AI for Science Executive Order—the Genesis Mission. The Administration has appropriately ambitious goals here; we may be on the verge of world-changing breakthroughs. Congratulations to all involved!

English
0
40
493
85.2K
Econolicious ری ٹویٹ کیا
Andrej Karpathy
Andrej Karpathy@karpathy·
A number of people are talking about implications of AI to schools. I spoke about some of my thoughts to a school board earlier, some highlights: 1. You will never be able to detect the use of AI in homework. Full stop. All "detectors" of AI imo don't really work, can be defeated in various ways, and are in principle doomed to fail. You have to assume that any work done outside classroom has used AI. 2. Therefore, the majority of grading has to shift to in-class work (instead of at-home assignments), in settings where teachers can physically monitor students. The students remain motivated to learn how to solve problems without AI because they know they will be evaluated without it in class later. 3. We want students to be able to use AI, it is here to stay and it is extremely powerful, but we also don't want students to be naked in the world without it. Using the calculator as an example of a historically disruptive technology, school teaches you how to do all the basic math & arithmetic so that you can in principle do it by hand, even if calculators are pervasive and greatly speed up work in practical settings. In addition, you understand what it's doing for you, so should it give you a wrong answer (e.g. you mistyped "prompt"), you should be able to notice it, gut check it, verify it in some other way, etc. The verification ability is especially important in the case of AI, which is presently a lot more fallible in a great variety of ways compared to calculators. 4. A lot of the evaluation settings remain at teacher's discretion and involve a creative design space of no tools, cheatsheets, open book, provided AI responses, direct internet/AI access, etc. TLDR the goal is that the students are proficient in the use of AI, but can also exist without it, and imo the only way to get there is to flip classes around and move the majority of testing to in class settings.
Andrej Karpathy@karpathy

Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be "diselenium diphosphide" and a spelling mistake (should be "thiocyanic acid" not "thoicyanic") :O

English
933
2.5K
16.7K
2.5M
Econolicious ری ٹویٹ کیا
Steven Pinker
Steven Pinker@sapinker·
Bjorn Lomborg, an early survivor of 21st century cancel culture, has long raised vital questions. Rather than disputing his logic or conclusions (which he would be the first to admit could be wrong), academics & activists tried to demonize & silence him, a trend that grew. @Marian_L_Tupy recounts the history. quillette.com/2025/11/20/a-v…
English
0
719
3.6K
424.9K
Econolicious ری ٹویٹ کیا
Jon Hartley
Jon Hartley@Jon_Hartley_·
On the latest episode of @capandfreedom, I talk with economist @DavidRHenderson about his career, the role of property rights and market competition in economic growth, the UCLA School of Economics (especially Armen Alchian and Harold Demsetz) and communicating economics online
Hoover Institution@HooverInst

Hoover Research Fellow @DavidRHenderson joins @Jon_Hartley_ on @CapAndFreedom to discuss his career as an economist, the role of property rights and market competition in economic growth, the UCLA School of Economics, Armen Alchian, the New Institutional Economics, and more.

English
1
3
16
2.6K