frenchmajesty

Cool concept! However, the fact that it's on a timer and you can only try the next even in 1m is a killer feature (in a not-good way). Same for not being able to view the leaderboard

Historically this has never flown.

There's only 1 billionaire for every what, 10M people, 100M ? They are outnumbered. At some point the underclass may band together and kick off a revolution to overthrow the ruling class.

Kings have gotten their heads chopped off when the people had enough.

I can see a version of history where the end of capitalism was AI and the AI-owning class with their robots and capital essentially dispose of the majority of the society. Society decides this system is screwed and decides to overthrow capitalism and we invent a new system.

After all, at some point, smart people came up with capitalism to solve the previous system's problems. We may not go to socialism but invent something new entirely to address the flaws of late stage capitalism.

Yea it ends on that date. I cashed out with $622K

I do get answers. The ones who typically said can't disclose are you full of shit. Crack teams know they're cracked and they will tell you.

"I'm a MIT-trained security engineer; I'm an ex-VP at Paypal, etc..."

Damn. Now I understand VC's a little better.

Some deals I saw "damn the traction is off the chart" and I didn't even care to ask any question I just threw money at them. I saw one startup named Salesforce, a CRM. I guess hindsight is 20/20 on that one lol. Didn't even read the pitch.

This game is awesome

Fun game! My investing strategy is to flush out quickly who's the team, what's the traction, what's unique insight into the market.

Bullshitters have trash or no answers. Killer companies have one of those 3 that is usually very compelling.

OP here. I should've added that clarification but it was to say as someone with the "most to gain" financially or professionally from AI becoming more important, I'm still against this content trend and find it is unproductive.

The ideas submitted still go through you where you approve/reject.

Good platform. A similar one was made I used to use back in ~2020 but eventually I think it died.

The best addition would be to have a simple form where people can submit ideas for questions. It'll keep your site from being stale and fading out of relevance like the last one.

You are looking at it wrong. Meta is a business. You know what they sell? Ads.

In fact, they are the #1 or #2 place in the world to sell an ad depending on who you ask. If the future turns out to be LLM-driven, all that ad-money is going to go to OpenAI or worse to Google; leaving Zuck with no revenue.

So why are they after AI? Because they are in the business of selling eyeballs placement and LLM becoming the defacto platform would eat into their margins.

I get a Heroku error trying to view the site.

Hey OP here. You're not wrong! Leaving aside the philosophical debate (isn't all form of capitalist participation selfishly motivated?), the main motivator was to help me and my friends with a problem we struggled with.

Many solo Entrepreneurs you see on Twitter with large audiences are busy people so they have hired cheap labor from India / Philippines to be the social media manager. They often take on the task of keeping up with the niches and drafting post ideas. The big issue is that the variance in quality of who you hire is very high, and it's also a mental and energy toll to manage an employee who works on the other side of earth.

So the AI helps to scours "here is what all the tech bros are talking about since 3 days ago" and then drafts 3-5 posts and shows them to me so I can curate. I get to keep my page and audience engaged while protecting my time from actual deep work instead of scrolling the feed all day.

Hey OP here. The use-case is to give an Agent the ability to post on my behalf. It can use these class labels to figure out "what are my common niches" and then come up with keyword search terms to find what's happening in those spaces and then draft up some responses that I can curate, edit and post.

This is the kind of work you typically hire cheap social managers overseas to do through Fiverr. However, the variance in quality is very high and the burden of managing people on the other side of the world can be a lot of solo Entrepreneurs.

OP here. I agree! I should've called out why I did _not_ follow that approach as many others have commented the same.

The main reason why is that I needed the classification to be ongoing. My system pulled over thousands of tweets per day and they all needed to be classified as they came for some downstream tasks.

Thus, I couldn't embed all tweets, then cluster, then ...

OP here. We embed both the label AND the tweet. So if tweet A is "I love burgers" and tweet B is "I love cheeseburgers", we ask in our vector DB if we have seen a tweet before that is very similar to B? If yes, we skip LLM altogether (cache hit) and just take the class label that A has.

OP here. I agree with you. For production use we use VoyageAI which is usually 2x faster than OpenAI at similar quality levels (p90 is < 200ms) but we're looking at spinning up a local embedding in our cloud environment, that would make p95 < 100ms and make cost negligible as well.

Op here. Yes that's right. We do also insert the current text embedding on misses to expand the boundaries of the cluster.

For instance: I love McDonalds (1). I love burgers. (0.99) I love cheeseburgers with ketchup (?).

This is a bad example but in this case the last text could end up right at the boundary of the similarity to that 1st label if we did not store the 2nd, which could cause a cluster miss we don't want.

We only store the text on cache misses, though you could do both. I had not considered that idea but it make sense. I'm not very concerned about the dataset size because vector storage is generally cheap (~ $2/mo for 1M vectors) and the savings in $$$ not spend generating tokens covers for that expense generously.

OP here. Yes that works too and get you to the same result. Remove risks for bias but the trade-off is higher marginal cost and latency.

The idea is also that this would be a classification system used in production whereby you classify data as it comes, so the "rolling labels" problem still exists there.

In my experience though, you can dramatically reduce unwanted bias by tuning your cosine similarity filter.

OP here. This is true. If you make your min_score .99 you can have very high confidence in copy-pasting the label, but then this is not very useful. The big question is then how far can you get from 0.99 while still having satisfying results?

OP here. It depends what you use it for. You do want the tags if you intend to generate data. Let's say you prompt an LLM to go tweet on your behalf for a week, having the ability to:

- Fetch a list of my unique tags to get a sense of my topics of interests

- Have the AI dig into those specific niches to see what people have been discussing lately

- Craft a few random tweets that are topic-relevant and present them to me to curate

Is very powerful workflow that is hard to deliver on without the class labels.

OP here. This is exactly right! You perfectly encapsulated the idea I stumbled up so beautifully.

Thanks for sharing I enjoyed reading this.

Time to sell

I'm sure Big Tech has an anti-conservative bias in its moderation but to go as far as to say Biden pressured them to do this? Lol. I'm much more likely to believe Trump team bullied them into signing this declaration than anything else.

Page for case studies is broken. Beyond that, the idea sounds interesting but I find myself incredibly skeptical of this product.

The overall sense I got is that this site has too much bloat and isn't focused on the most important thing: Why should I trust you can deliver on the promised value prop?

The proposed design in this paper is bad, but the core of the idea is very interesting.

At a high-level, 90% of the complexity of their data retrieval system can be deleted by simply having attaching a `CLAUDE.md` file to every data store that is automatically kept up to date the agents can read.

High-throughput queries by an agent don't feel much different than high-throughput querying that large scale systems Instagram and Youtube need to service on a daily basis. Whatever works for 10M active users per second on IG would also work for 50 agents making 1M queries per second.

I can see a need for innovation in data store still. My little startup probably can't afford the same AWS bill than Meta but the tide would lift all boats, not just AI-specific use cases.

Very impressive but not surprising coming from Meta. They have an history of doing this kind of things.

Back in the early 2010s, they found a way to spy on HTTPS traffic on the iOS App Store to monitor which apps were getting popular. That's what allowed them to know WhatsApp and Instagram were good acquisition targets.

At this point, I think the race for Zuckerberg is, can Meta survive long enough for the next platform shift (AR or VR) where they will own one of the major platforms and won't need to abide by any reasonable rules before their "internet tentacles" that sustain the Ad Machine are cut off.

My bet is they will make it. Though I don't wish it, they're on track.

I disagree with the author here. His point can be summarized as "LLMs produce bad code, LLMs lead to the teams's average skills decreasing and they can't maintain large codebases over time".

Yet nowhere he addresses the #1 flaws to his position: rate of improvement of the technology, and its promise to deliver on saved money and gained speed.

In all the companies I've seen engineering leadership hardly really gives a shit about things OP says are important. They just care that customers are happy, the system is stable, and its malleable enough to allow for pivots when need be.

Good discussions & documentation about architecture before starting the work that gets peer-reviewed + A non-stupid engineer putting on good guardrails around the LLM's output + the extensive unit test suites in CD/CI + peer reviews on the PRs = all downsides near eliminated while all upside gained.

This is how we work at my company today (health startup). Google and Meta also boast publicly +30% of new lines of code are AI-generated in their companies today. That the state of *today*; assume in 5 years these AIs are 10x better... I simply cannot foresee a world where LLM-assisted coding is not the de-facto way be a software engineer.

Funny you should ask I just ended up here googling "graph memory LLM"

So yea I'm very much looking into it. I want my personal agent to grow to know me over time and my life is not bunch of disparate points spread out across a vector space. Rather It's millions of nodes and edges that connects key things. Who my parents were, where I grew up, what I like to do for fun and how it ties into my personality and strengths, etc...

To have this represented in a graph which a model can then explore would allow it to make implicit connections much easier than attempting the same with embeddings.

Hey, OP here. I agree.

If you get a list of all the startups that got acquired or IPO in the last 10 years, you will find it's extremely rare the technical co-founder is still around. The staying rate for CEO is like 99% while the staying rate for CTO is more like 50% (making up numbers here but this is directionally right).

With enough scale, a great CTO can be hired for the right salary. The way I answer this for myself is two-fold:

1. I've vowed I will never be the second chair guy because I don't wanna get pushed out.

2. It's important to up-skill yourself so you can contribute more value than a glorified engineering manager by driving vision, being a headhunter of superstar engineers, among others high-value skills