< Back to the archive

Like what you see? Subscribe here and get it every week in your inbox!

Issue #215 - April 23, 2023

Here are the top threads of the week, happy reading!

Top comment by iamwil

Think of it more as "prompt-fu", akin to "google-fu"--or how to google. You do have to know how to talk to an LLM, and it will be important. But it's not so much engineering, as we come to think of it in software traditionally. I wouldn't get hung up on the name, but just see it for what it is--a bad name for something we'll need to learn to be effective. It won't go away entirely, but will be mitigated to be less important as LLMs and AI get better.

Top comment by Nokinside

Semiconductor industry has the deepest and most complex value chain in the economy.

TSMC has always been pure fab company and it pays off now. Samsung and Intel are also in chip design business and do other things. They are less focused. TSMC's lead is not guaranteed. Any new technology node can fail and remove them from competition if they make wrong choices.

I'm not exaggerating when I say that designing a new technology node for mass production is like a moon program. TSMC designs new node every few years, builds a fabs that cost 20+ billion. ASML machines are the most expensive tooling there but they are just part of the whole.

Intel and Samsung are almost as good, but small differences have huge impact in the final result and timing. Small percentages in final yield can make a difference.

Top comment by nelsoch

Semiconductor company laid me off after working there since 2018. I kept a lot of leaks quiet and helped save a lot of trouble/money. Went above and beyond the call of duty and even relocated my wife and kids to be closer so that I could be on-call(not in job description). I took leadership and management positions without compensation just to keep workflow going. Although I had clearly indicated I was interested in those positions, I was blocked from them because I was not going to be compensated for the additional responsibility.

Now I'm left with a mortgage, debt and other payments that Unemployment can't begin to cover.

I asked if I could keep my job or get relocated to another dept- 'No'.

Everything is frozen- everything is stagnate and people are afraid of more layoffs happening for both contract workers and direct-hires.

I tried for years beforehand- to get moving up, but told it wasn't possible(yet). I even tried playing the 'I have another offer elsewhere' lie card, with nothing to show for it.

What's additionally frustrating, is that many local retail places won't hire me.

My experience at the company has cut me off from other work- for fear that I may not stick around for the long-term.

DoorDash is no longer taking applications in my area(that was a shock). Retailers wont take me because of my accomplished work history. Lyft/Uber wont allow me to work for them because my car is too old.

I have applied to soo many Craiglist, HN, Dice, Linkedin, Indeed, Gov and GlassDoor jobs that I my feeling of self-worth had diminished what has felt like eons ago. It's not that I don't get decent offers- it's that I get turned down relatively quickly despite my time at Semiconductor Co.

I'm at the point where I just want any income- the desperation to feed and provide for my wife and kids is what's driving me right now.

Top comment by jonahbenton

Yes. It is your life. It isn't about what is out there. It's about what's in you.

My kids are 19, 17, 12. I tell them- you're not going to college to get an education that is about knowledge out in the world. You are going to get an education about you. To learn about your person- your body, your brain, your own mental model of your self and other selves and the world.

Your person is still in physical growth mode until at least 25, and then you have lots of other changes and challenges coming after that. You will continue learning, including about your self, throughout the entirety of your life. To be set up to do that is why you're going.

(Yes, college is not the real world, in any way. But in important ways it is real enough.)

==

The most important things to be able to do are- build relationships, focus and concentrate, organize your self and your thinking, communicate, have fun, and take care of the physical self. You don't have any idea, really, how well you do those things as a teenager. It's the job of the adults around you to help. College is an opportunity to expose your person to more unique, distinct, varied, skilled adults and peers than at any time previous, and for some, more than they will ever get again (unfortunately). That exposure is the most intense learning the self can do.

For each of my kids, they have things they are good at now, and things they are not good at. Not just skills- capabilities. Biases. Potentials, not actuals. As their parent I have a good sense of possible distinct and unique trajectories for each of them given those potentials, and I do what I can to coach them onto those various trajectories and in specific work domain disciplines that are potential fits (to my eyes) for them. But that's a conversation that is specific to our relationship. And their lives are their own.

For you, I would encourage you to see yourself not even at the beginning of your adventure, and to think hard and figure out good ways, with the guidance of adults you currently respect and trust, to avail yourself and position yourself to be exposed to and learn from new adults worthy of respect and trust. And pay it forward, too.

Top comment by VLM

The philosophy of postgresql was to do the best possible job the rightest way. Not necessarily the easiest to use nor fastest.

The philosophy of mysql was to do the best it can as fast as it can for as many users as it can. Not necessarily the 'right' or 'best' way.

Its not like either philosophy is formally documented or mandatory but "generally" matches up pretty closely to real world behavior.

The biggest problem you'll have evaluating them is both products are incredibly old and have changed over the decades so you'll find plenty of web search results DEMANDING that mysql can't do transactions, for example, because that was written 25 years ago and transactions were pretty much a solved problem some decades ago on mysql. Similar issues exist for tooling, library support, clustering, I wouldn't trust a many years old blog post for either product LOL.

Top comment by abdullin

Great question!

1. I've observed multiple products across customers.

1.1 Correcting or filling missing information in structured data. For example a system to suggest corrections to products in a company catalogue (each product category has different schema). Unstructured data is pulled from various websites and optionally from categories retrieved from images. It is then compared against the data and most probable fixes are reported.

Most of the work is done by a few polite prompts to GPT3.5/4 (~5 English sentences in total)

1.2 Better search company data. E.g. a chat bot for internal documentation that can also access internal services in order to answer a question. Same ~5 English sentences to do bulk of the work.

1.3 (non commercial) Endangered language preservation. Building a smart agent that is accessible via chat/hardware (like Alexa/Homepod), that talks in native language can understand and helps to preserve the culture. This is a complex one.

2. Tech stack itself is rather simple. Mostly - GPT, LangChain/LlamaIndex, Vector database with embeddings for memory, plugins for external services and potentially agents to drive workflows.

Output quality, testing, monitoring, scalability etc also don't differ much from operating normal "old-school" ML models. If anything, it feels simpler.

The tricky part is that the entire notion of LLM-driven micro-services is new. Quality of the resulting product largely depends on knowing prompting tricks and following the latest news in an area.

Plus the biggest challenge that customers want to be solved: "How can I ran it on my hardware?"

Top comment by l1n

You might like this CGP Grey video that explains it pretty well: The Better Boarding Method Airlines Won't Use https://www.youtube.com/watch?v=oAHbLRjF0vo

Top comment by onion2k

I'm an idea guy by heart.

Try to lose this notion.

The key to success in a startup (apart from timing, luck, having the right idea, grit, focus, etc) is determination to see things through to completion. You have to believe in your idea and see it through to the end, where 'the end' is hopefully an exit of some sort probably years in the future. If you see yourself as "an idea guy" you will be distracted by the new shiny thing you think of, and if that happens when your startup is in a slump you'll give up before you see success.

You do need to be "an idea guy" to build a startup, but all the ideas need to be about driving the core idea forwards. You need to see yourself less as "an idea guy" and more as "a guy".

To that end, I'd recommend starting a side project to see if you can grow it without getting bored, giving up, etc.

Top comment by rektide

Verizon fios, 100mbos, $65. Major (for us) metropolis, East coast USA. They turned on IPv6 like 2 maybe 3years ago, yay.

I'd love a gratis bump to 200mbps some day.

Edit: oh snap! It was pretty hard to find plans on the website (most pages wanted me to check availability with address/email/phone... No) but I did eventually find a page that told me there's a 300mbps for $55 - $10 if I use a de it card. Called them, and done! This post saved me money & tripled my speed.

I have a very expensive grandfathered Verizon unlimited wireless plan with no softcap (but they'll drop me if I use 100GB or so repeatedly). Alas it's not qualified, otherwise I'd save another $20!

Top comment by wilsonnb3

You aren’t going to be able to tell which companies have developers using LLM’s and which don’t, in the same way that you can’t tell who is using intellisense and who is using vim.

It helps you code somewhat more efficiently, like many of the other tools we have, but doesn’t help with the hard parts of software development.