*"This is a 1 hour general-audience introduction to Large Language Models: the core technical component behind systems like ChatGPT, Claude, and Bard. What they are, where they are headed, comparisons and analogies to present-day operating systems, and some of the security-related challenges of this new computing paradigm."*

Andrej Karpathy - Intro to Large Language Models [Video]

Hi I'm Jeremy. I'm building this site because I'm not satisfied with other online community type websites and their lack of innovation (see the /about page). The goal is to make a superior, more open, and more decentralized online community.

The site is still in early stages in active development (see the dev masterthread here: https://zsync.xyz/p/zsync-dev-update-masterthread)

Join us if this sounds interesting! Feel free to send me any feedback or reach out directly!

*"While self-correction has shown promise in improving LLM outputs in terms of style and quality (e.g. Chen et al., 2023; Madaan et al., 2023), recent attempts to self-correct logical or reasoning errors often cause correct answers to become incorrect, resulting in worse performances overall (Huang et al., 2023). In this paper, we break down the self-correction process into two core components: mistake finding and output correction. For mistake finding, we release BIG-Bench Mistake, a dataset of logical mistakes in Chain-of-Thought reasoning traces. We provide benchmark numbers for several state-of-the-art LLMs, and demonstrate that LLMs generally struggle with finding logical mistakes. For output correction, we propose a backtracking method which provides large improvements when given information on mistake location. We construe backtracking as a lightweight alternative to reinforcement learning methods, and show that it remains effective with a reward model at 60-70% accuracy."*

LLMs cannot find reasoning errors, but can correct them

The New PS5 SLIM is just around the corner! 5 things you need to know.

Show HN: <https://news.ycombinator.com/item?id=38285228>

*"I built a simple React/Python app that takes screenshots of websites and converts them to clean HTML/Tailwind code.*

*It uses GPT-4 Vision to generate the code, and DALL-E 3 to create placeholder images.*

*To run it, all you need is an OpenAI key with GPT vision access.*

*I’m quite pleased with how well it works most of the time. Sometimes, the image generations can be hilariously off. See here for a replica of Taylor Swift’s Instagram page: [https://streamable.com/70gow1](https://streamable.com/70gow1) I initially had a hard time getting it to work on full page screenshots. GPT4 would code up the first couple of sections and then, get lazy and output placeholder comments for the rest of the page. With some prompt engineering, full page screenshots work a whole lot better now. It’s great for landing pages."*

Convert any screenshot into clean HTML code using GPT Vision (OSS tool)

Bitcoin exchange-traded funds (ETFs) have gained popularity as a financial instrument, offering several benefits for investors. Here are some key advantages associated with Bitcoin ETFs:

1. **Accessibility and Convenience:**

   - **Mainstream Investment Vehicle:** Bitcoin ETFs provide a familiar and regulated investment vehicle for traditional investors who may be hesitant to directly invest in cryptocurrencies. This can attract a broader range of investors, including institutional players.
   - **Ease of Trading:** ETFs are traded on traditional stock exchanges, making them accessible through regular brokerage accounts. This eliminates the need for investors to set up and manage digital wallets, private keys, and navigate cryptocurrency exchanges.

2. **Regulatory Oversight:**

   - **Regulatory Approval:** Bitcoin ETFs operate under the regulatory framework of traditional financial markets. This provides a level of oversight and investor protection that is often lacking in direct cryptocurrency investments. Regulatory approval can enhance investor confidence and attract institutional capital.

3. **Risk Mitigation:**

   - **Diversification:** Bitcoin ETFs can offer investors exposure to the price movements of Bitcoin without the need to hold the actual cryptocurrency. This allows for diversification within a traditional investment portfolio, helping to spread risk across different asset classes.
   - **Custody Solutions:** ETF providers typically employ secure custody solutions for holding the underlying Bitcoin, addressing concerns related to theft, hacking, or loss of private keys.

4. **Liquidity:**

   - **Market Liquidity:** ETFs are traded on established stock exchanges, providing high liquidity compared to some cryptocurrency exchanges. This liquidity can be especially beneficial for large institutional investors looking to buy or sell significant amounts of Bitcoin without causing substantial price slippage.

5. **Transparent Valuation:**

   - **Net Asset Value (NAV):** Bitcoin ETFs regularly disclose their Net Asset Value (NAV), providing investors with transparency regarding the fund's underlying value. This can help investors make informed decisions based on the fund's performance and market conditions.

6. **Tax Efficiency:**

   - **Tax Treatment:** Investing in Bitcoin ETFs can offer tax advantages compared to direct cryptocurrency investments. Capital gains taxes may be more straightforward, and investors may benefit from the tax efficiency associated with traditional investment structures.

7. **Market Integration:**

   - **Integration with Traditional Markets:** Bitcoin ETFs bridge the gap between the cryptocurrency market and traditional financial markets. As they become more integrated, the correlation between Bitcoin and traditional assets may evolve, potentially offering new opportunities for risk management and portfolio optimization.

8. **Institutional Adoption:**

   - **Attracting Institutional Investors:** The regulatory framework, transparency, and risk mitigation features of Bitcoin ETFs make them more appealing to institutional investors. As institutional participation in the cryptocurrency market increases, it can contribute to greater market stability and acceptance.

While Bitcoin ETFs offer various benefits, it's essential for investors to carefully evaluate the specific ETF structure, fees, and regulatory environment before making investment decisions. As with any investment, there are risks involved, and market conditions can impact performance.

Explore the Benefits of Bitcoin ETFs

Troye Sivan has so many bangers it's ridiculous. I heard this song on the radio and that chorus been stuck in my head since.

Troye Sivan - Got Me Started

I will post dev updates as comments in this thread.

Feel free to comment with any requests / feedback / thoughts

ZSync Dev Update Masterthread

Here’s a summary of my lessons learned living in Europe, Asia, and South America over 5 years as an American.

Asian cities like [Seoul](https://jsavage.xyz/2022/03/30/why-seoul-is-the-best-modern-city/), Singapore, and Tokyo are way more advanced than us. Doesn’t even come close. People take pride in their work, no matter how menial. These cities are by far the cleanest and safest. Trains leave exactly when scheduled. Things just work. People have high standards, as reflected in tasteful interior designs in cafes. I see more technological innovation and automation here than anywhere. Governments are able to mobilize and get things done (eg. Korea developed COVID tests in only 1 week, whereas the U.S needed another 5 weeks). More cheap, delicious, healthy food options available at any time of the day/night than anywhere in the world. Greatest density of things to do, with commercial establishments literally stacked on top of each other like a mall (I wish the rest of the world would borrow this). Highest concentration of public work cafes of anywhere. The downside is that countries like Korea and Japan have the worst work cultures (eg. long hours even if you’re doing nothing, little vacation), are overly obsessed with prestige, overly conformist, have weak entrepreneurial cultures, and governments are more prone to [authoritarianism](https://jsavage.xyz/2022/03/30/my-experience-in-south-koreas-mandatory-7-day-quarantine/).

Europeans have the healthiest perspective on work/life balance (1-3 months vacation, fewer work hours, people recognize that life is more than just your job), the sanest governments, and public transportation so good you don’t need a car (you can travel the whole continent by rail and bus). In most European countries basic human services like education and healthcare are free or practically free (in Denmark students even get paid a stipend to go to university). Government systems tend to be parliamentary multi-party systems that greater represent the will of the people. [Switzerland has the best government system in the world](https://jsavage.xyz/2022/03/24/why-switzerland-has-the-best-government-system-in-the-world/) with its referendum system. Homelessness although greater than in east Asia is very rare, unlike the U.S where there’s so much endlessly increasing rampant homelessness you feel like the apocalypse is imminent. Generous welfare systems means that in many countries you don’t have to wage slave and stress about destitution, and worker protection laws means that you can’t get fired unless you really do something terrible. Everyone is well-traveled, cultured, and speaks multiple languages. I was shocked to learn that in countries like Denmark and Germany it is the norm to take a gap year after high school to travel the world. I’ve found that European people (which is a huge generalization since Europe has 44 countries) seem to have the highest level of intelligence and independent thinking, and tend to be much more honest and straightforward than Americans.

The downside of Europe is that it’s not the most modern or advanced (Asia wins there), tech salaries suck, there’s less of a culture of entrepreneurship, and there are few proper megacities. Stores are open less hours, especially in countries like Italy and Spain where they have siesta. Some countries have very high tax rates, though as an American who lived in a state with one of the highest tax rates (NYC), I was shocked to learn that my tax rate in the U.S was higher than in countries like Switzerland that actually have functional government systems (eg. healthcare, welfare). Also there’s a massive difference between European countries. Switzerland for example has automated checkout machines in grocery stores, whereas I never saw that nearby in Rome, Italy. Whereas countries like Switzerland and Estonia are highly efficient, Mediterranean countries like Spain, Italy, and Greece are notorious for having awful bureaucracies, and their economies are not exactly thriving.

The U.S is money-obsessed, workaholic, cutthroat, completely lacking in public transportation (outside of NYC you pretty much need a car everywhere), lacking in proper cities with most of the country looking like a giant strip mall / parking lot, outrageous levels of [poverty](https://jsavage.xyz/2019/07/31/poverty-is-a-human-choice/) and [homelessness](https://jsavage.xyz/2019/10/31/is-it-possible-to-live-in-nyc-and-have-a-moral-conscious/), [dysfunctional ultra-polarized failing two-party government system](https://jsavage.xyz/2019/08/16/americas-failed-democracy/) where no one feels represented, failing government that can’t handle taking care of basic services like healthcare and education, and rampant guns and mass neverending shootings. Most Americans are not well traveled (63% of Americans do not have a valid passport). Perhaps the biggest achilles heal of America is that Americans delude themselves into believing that America is the greatest country on the planet, and due to this arrogance make no effort to learn from other countries even when America’s inferiority is completely and objectively obvious (eg. America’s healthcare system).

The U.S is very diverse with people of every ethnicity. Everyone (except for Native Americans) is an immigrant, it’s just a question of how far back your ancestors immigrated. This diversity is probably party responsible for the lack of empathy people have for one another as reflected in the lack of universal healthcare and welfare. The positive however is that racism is less rampant in the U.S, and anybody can choose to become an American (whereas no matter how long you live in Japan, you will never be considered Japanese).

American people do tend to be friendly, warm, and outgoing. I also find Americans more likely to be entrepreneurial and ambitious, particularly in cities like NYC and SF. The downside is that Americans tend to be significantly faker (eg. the stereotype of two American girls pretending to be so excited to see each other and talking about needing to make plans, but then never talk to each other again), and overly afraid to talk about “controversial” (ie. interesting) topics like politics. I find it significantly easier to talk about politics and other divisive topics with Europeans, whereas Americans are often completely uncomfortable to talk about those things, whether due to fear of offending other people or a strange emotional attachment to their beliefs. Also I think that Americans are more likely to be arrogant, lacking in empathy, and crazy (though crazy can sometimes be a good thing). In Europe and Asia you tend to have less of the extremes.

South American people are the warmest, most outgoing, most laidback, most physical, and most sexual. There is more gender polarity in South America than in western Europe or the U.S – where some feminists will go as far as to cry oppression when a man opens a door for them. South Americans are by far the best dancers, with Latina women having an incredible natural ability to move their hips. The nightlife in South America is the best. If Americans live to work and Europeans work to live, then South Americans are further on the “work to live” spectrum than the Europeans. Unlike with Germans or the Swiss, punctuality is not an expectation.

The downside is that this greater warmth also comes with greater fakeness. Colombian women are notorious for flaking because they try so hard to be polite that they’ll accept dates even when they don’t have any intention of showing up. My friend who lived in Medellin was frustrated when he’d repeatedly arrange meetings with this neighbor (to discuss a complaint) only to find the neighbor wouldn’t show up. The prioritization of life and fun means that intelligence levels seem to be lower on average. There’s a stereotype of men being more prone to commitment issues.

It’s hard to generalize South American countries because there is such enormous variation between cities like Sao Paulo and Bogota. But overall I was very impressed with cities like Sao Paulo and Buenos Aires, with parts of Sao Paulo often looking nicer than NYC. Bogota on the other hand is an objectively ugly and dangerous city. Overall however, South American countries have the highest poverty (eg. favelas), highest crime, and most corrupt governments.

I’ve found that poorer “third world” countries are often just as developed as first world countries, just cheaper and with lower salaries so imports are more expensive (eg. electronics). Cities like Kyiv and Belgrade look just as good if not better than many cities in the U.S and western Europe, just with prices at a fraction of the cost (again I prefer European cities to American cities because you don’t need a car in European cities due to walkability and public transportation). Despite salaries being significantly less in Kyiv and Belgrade, you will see few homeless people whereas in Los Angeles, San Francisco, and NYC you will see homeless people everywhere and sidewalks lined with tents. I think Americans would be shocked to see how well the rest of the world lives.

---

I think there’s a lot that countries can learn from each other. As an American, I hope that America will borrow the walkability and public transportation of Europe and Asia, the technological advancement, innovation, and high standards of Asia, the government competency, empathy, and healthy perspective on work/life balance freedom of Europe, and the warmth and fun of South America. America’s diversity, inclusion, culture of entrepreneurship, and friendliness are definitely strengths that would benefit from borrowing from the strengths of other cultures.

What the U.S. Can Learn From Europe, Asia, and South America

Ethereum Merge Completed

Can AI Ever Understand How Humans Think? - YouTube

What I believe to be one of the most underrated features of LLMs is the ability to convert imprecise human text into code.

In the past, writing a computer program required writing code - aka writing text in a very specific, tedious way such that it can be understood by a computer. A single erroneous character will crash an entire program. Writing code is difficult and tedious enough that it is a professional career that tends to require some degree of study (eg. 4 year CS degree, coding bootcamp), and the job can command annual compensation packages from $100k-$1m+/yr.

LLMs for the first time enable writing programs through natural language, ie. without writing code.

What this will do is make it dramatically easier to create computer programs. The technological jump is the equivalent of trying to talk to someone in Icelandic in 1989 (assuming you don't speak Icelandic), and then suddenly being given access to a modern smartphone with Google Translate.

Some implications:

- Anyone will be able to easily create or update computer programs
- Computer programs will easily be able to create computer programs
- Coding for the first time in history will just be done by regular human language instructions that any non-technical person can write. A disgruntled customer or product manager will simply be able to create a bug report or feature request, and an AI agent will immediately be able to take that and update the codebase (eg. submitting a pull request after testing and code reviewing its own work)
- Programming languages will become unimportant, because any language will easily be able to be translated into any other
- Coding will be commoditized

The human programmer is the translation layer between the human and the machine, and AI is automating that work away, just like it's automating human language translators.

*AI skeptic: So what? Who cares if some geeks can make computer programs easier?*

AI and automation are computer programs!

**AI is making it easier to improve AI.**

This is a feedback loop that results in exponential growth of AI. The more AI improves, the more AI is able to improve itself. Eventually this feedback loop gets so out of control that humans cannot keep up, a point known as the "singularity".

Humans are terrible at comprehending exponential growth, and thus I believe are drastically underestimating how quickly this is all developing.

Most seem to think that the job market for most people is going to be fine over the next decade - I vehemently disagree. I believe that AI will dramatically change society over the next few years and make the workforce drastically more competitive as AI starts to outstrip human ability. The labor market will become so competitive that UBI will become inevitable (I've been saying this for a decade, but never before has it looked so obvious and imminent).

The nature of work will move to a higher level of abstraction. Workers will become more like managers who delegate the "grunt work" to AI - responsible less for the nitty gritty of implementation and building tedious things, and responsible more for deciding what to build and where to direct the AI agents' focus. Just like fast mental math skills hasn't really been a competitive advantage since the invention of the calculator, doing any sort of repetitive, automatable work will not be of any advantage because the AI will be able to do it faster and cheaper at a speed of gigabytes/s, while being able to self-correct and debug itself. As tech becomes commoditized, humans will have to focus more on the "human" aspect such as marketing and zero sum games to economically compete.

The mistake that people who dismiss this tend to make is that they often believe that AGI is required for this mass societal transformation. I disagree. All it takes is for computer programs to be able to make the creation of computer programs easier to achieve this AI flywheel effect.

Anyways just some random thoughts here at 2:11am in Seoul.

LLMs create an Exponential Flywheel for AI Advancement

HN: <https://news.ycombinator.com/item?id=37345727>

Everything I wish I knew before moving 50,000 lines of code to React Server Components

Wavacity – a FOSS port of Audacity to the web

"Amazon CEO Andy Jassy has a message to employees who don’t want to return to the office: “It’s not going to work out for you.” That’s according to [a report from *Insider*](https://www.businessinsider.com/amazon-andy-jassy-rto-office-policy-employee-jobs-2023-8), which says Jassy made that statement during a meeting earlier this month.

While [Amazon ordered its employees to return to the office](https://www.theverge.com/2023/2/17/23604485/amazon-return-to-office-three-days-a-week) for three days per week starting in May, many Amazon employees weren’t happy about the decision. [Thousands of workers signed a petition](https://www.businessinsider.com/amazon-hr-chief-rejects-petition-against-return-to-office-policy-2023-3) against the mandate and [staged a walkout in response](https://www.cnbc.com/2023/05/31/amazon-workers-plan-to-walk-out-over-lack-of-trust-in-leadership.html)."

Amazon CEO reportedly told remote employees: ‘It’s probably not going to work out’

HN: <https://news.ycombinator.com/item?id=37301991>

WebLLM: Llama2 in the Browser

66% of Americans want European-style vacation policies, like being OOO for the entire month of August

It's clear that we're approaching the singularity, & most are drastically underestimating the impact that AI will have on society within the next couple years. Some predictions:

\- Humans will not be writing code by hand in a few years.

\- Workers will be expected to move "up the stack" of abstraction. Software engineers will be expected to be more high level product manager hybrids, serving more as technical business managers who delegate low level tasks to AI agents + cheap offshore workers

\- Rise in generalists. Expensive specialists are most at risk since AI democratizes knowledge + power

\- Gutting of the middle class, since most peoples' jobs are now very easy to automate

\- Rise in AI agents. Most of what you read online including on internet forums and in DMs, you won't be able to tell if it was written by a human or AI (already the case with recruiting). There is currently an arms race in AI agent development, the results of which we'll start seeing on society within the next 12 months.

\- The glory days of working in tech are over. Just like very other industry, it's only going to get more and more competitive. Salaries will at best remain stagnant. This is not specific to tech and will be the case for every industry. The industries most resilient will be those that require a human (eg. physical therapy)

The winners will be those who harness AI to their advantage, the losers will be everyone else.

I think most people are drastically underestimating the enormous impact that AI will have on society within even just the next 12 months. People are treating AI like a temporary fad or bubble, as if things will just return to the way they were before. But AI is not only here to stay, it's just getting started, and it's an arms race because everyone knows that AI will eat everything. Humans are terrible at understanding exponential growth, and most cannot comprehend how fast things are about to change.

Not trying to make this political - but I don't see any easier method of alleviating the hemorrhaging of the middle class than governments implementing a Universal Basic Income (UBI). Humans just cannot compete with a superintelligent autonomous AI that has parsed every book and document on the internet. We can continue to be in denial of this while our citizens suffer and overdose suicide to cope with the depression and bleak opportunities, or we can embrace AI and leverage it to free people to spend their time at their own leisure, moving society collectively up Maslow's Hierarchy of Needs. But given how blind and reactionary most people are to this kind of stuff, I don't predict anything changes until we reach a serious boiling point, so unfortunately billions will needlessly suffer in the meantime until the masses wake up to the cosmic societal shifts that are taking place as we speak.

<https://twitter.com/jeremybernier/status/1695350480388714605>

Implications of Approaching the Singularity

I made a tax calculator mainly for IT contractors in Poland.

IT professionals earn from 4k - 7k EUR/month in Poland, where the cost of living is quite low compared to other Western EU countries.

See how much of tax you would pay as an IT contractor in EU, Poland

HN: <https://news.ycombinator.com/item?id=37250821>

Build a chatbot with custom data sources, powered by LlamaIndex

I really like this Japanese rap song, but you need to understand Japanese to appreciate it.

Basically the first verse is a kid on the playground talking about playing catch, his friends liking girls, and other childhood things. The chorus is him saying lets all play together forever, even when we're adults.

Second verse is a more grown adult in his 20s - talking about recording in the studio, having fun with his friends, on stage at the club, and "playing" everyday being his dream.

Final verse is a more grown adult in his 30s - talking about how time flies, his friends' jobs, those who've become fathers, others who've gained weight, and those who passed away (reference to his father who committed suicide when he was a kid) - saying one day they'll meet again.

The song is super nostalgic, I think especially for me since I actually spent some of my childhood in Japan.

It's a bit melancholic for me as well. There was a purity to childhood. But then after school you get thrust into the wild and have to make money. Some are able to make a living do what they love, but most can't - slaving away at jobs they have zero passion for for a paycheck (reminds me of this [classic Steve Cutts video](https://www.youtube.com/watch?v=BsjwrA_Oo18)). After university it becomes exponentially harder to make friends (unless one makes a conscious effort to), connections drift apart, people get into serious relationships and drift even further apart. The carefreeness of childhood turns into responsibilities, work, bills, stress, kids, etc. "Playing" and socializing becomes less frequent, with social interactions more resembling "networking" or "what can you do for me", and serious, distant conversations.

Of course that's a pessimistic take. There are great things about being an adult as well, and ultimately life is what you make of it. I think it's common for people to say that their childhood years were their best. But I will not resign to my best years being in my past, and will always strive to live to the fullest even into old age - always trying to keep that childhood playfulness, carefreeness, and curiosity.