ewild

Used to be a bakers oven was one per town, maybe big precise machine becomes cheap smol precise machine

there are mountains of evidence that postgres does indeed scale if thoughfully designed.

I had 20,000 Bitcoin at one point from selling RuneScape gold when I was 9.

oculus didnt ship a single product not owned by facebook.

And if an agent were to amass a large sum of Bitcoin you don't think people wouldn't do things for money? Especially if they don't realize they are doing part 1 of 160 parts that get it to the end goal of a virus?

The whole point is a 5 year old can solve it.

all of them are down lol

I don't feel my job is very safe anymore.

I actually have data on this albeit it's a bit skewed. None of our clients are dev like folk but they are financial folks. We sell financial data for big players so not the analysts (seat cost is over 50k per year) and of our ~10k users within the last 6 months of us launching MCP we have 1500 DAUs on the MCP

Because you're a dev thinking for devs. No 60 year old is going to use Claude skills with the CLI. If my customers want their AI to interact with my product and MCP is the best way about it.

It's rumored fable is around that 10T number

I guarantee you're a lot easier to manipulate than you think.

What about the kids they intentionally get driven to suicide by keeping the blue bubbles for no other reason than child indoctrination due to bullying from other kids.

I know there can be CTOs who write a lot of code and be good, but I hope to God you're not my CTO because he is a nightmare in this regard right now. We aren't even a startup anymore we have 80 engineers and he pushed 200k lines this week

My team (ML team) is using about 2-3k per day per person on a team of 9

They do. They all use ViTs and have for quite a while.

Is this ironic are we actually calling shit talking llms bigotry?

people really dont understand how the transformer works to think this is something trivial if possible at all

It's an incredibly privileged Pov to say it isn't a contest. These kids entire futures are impacted by these scores.

Pretty much the only one with a real consensus around it is creatine. And even that has debate around the right dose

This sounds like we are trying to add an LSTM into a transformer

At this point if someone calls it auto complete they can be written off as a Luddite with nothing valuable to say. The irony being they themselves are being a stochastic parrot by parroting the jargon other people say about llms.

I genuinely think it's part of a psyop. If we bloat all codebases and eventually start printing the models on chips to reduce inference costs by 50-100x they'll take in massive profits from 5M line codebases instead of 350k

Proof they don't nerf it only after testing that the benchmarks there stay the same? So overall performance degrades but they isolate those benchmarks?

Ok so in a situation like regular orchestration you would essentially layout all possible steps the LLM can take in your code in a big orchestration layer, and if it hits the sensitive endpoint the orchestration that can occur past that will block off web search. In the design that is. But for something like a manus style agent where you're outsourcing all the work but allowing it to hit your MCP it just becomes a regular API the LLM can call

I feel like I don't fully understand mcp. I've done research on it but I definitely couldn't explain it. I get lost on the fact that to my knowledge it's a server with API endpoints that are well defined into a json schema then sent the to LLM and the LLM parses that and decides which endpoints to hit (I'm aware some llms use smart calling now so they load the tool name and description but nothing else until it's called). How exactly are you doing the process of stopping the LLM from using web search after it hits a certain endpoint in your MCP server? Or is this referring strictly to when you own the whole workflow where you can then deny websearch capabilities on the next LLM step?

Are there any good docs youve liked to learn about it, or good open source projects you used to get familiar? I would like to learn more

he owns geico

i was at the cvs right next to the extra storage when the helicopters showed up and all the police it was kinda nuts to be so close to an event like this.

Soo probabilistic biases.

i have not written about it due to me being a silent partner in the company and dont want my name publicly attatched to it, but the code and prompts is all more like talking to a buddy is how i use it, i ask it to build specific things then i look through and make changes. For instance a few examples i can give is there is a lot of graph traversal in my data i built, I'm not an expert on graph traversal, so I researched what would be a good algo for my type of data, and then utilized claude to implement the papers algorithm into my code and data structures. I dont have the llm in any steps that the customer interact with (there is some fuzzy stuff but nothing consistently run) but i would say an llm has touched over 90% of the code i wrote. its just an upgraded rubber ducky to me.

If i wasn't experienced in computer science this would all fall apart however i do have to fix almost all the code, but spending 10 mins fixing something is better than 3 days figuring it out in the first place (again this might be more unique to my coding and learning style)