boredumb

You can pay for google docs+ via workspaces and they have an explicit customer data retention guarantee in their license.

You buy software that includes a commercial license that guarantees data retention

> LLMs are surprisingly biased towards picking "A", especially if they're otherwise not sure.

Not nearly as sophisticated as myself who would mutter "When in doubt - Charlie out" before marking C.

Just have a route that describes your API endpoints in a machine readable format, eventually they'll come to some consensus and in the mean time this works well enough to allow LLMs to plan.

ages ago I tried using IPFS to more or less accomplish this, I imagined it to act more like a weights/training data network fs that everyone would be able to participate in.

What happens if the gun is faulty and explodes killing the guy next to me and the family wants compensation?

In the US at least if a lawyer screws up a contract beyond what a competent lawyer would and causes financial harm they can be sued.

memes and snark aside, can you use this to create legitimate terms and contracts for my products and if I do who is getting sued when it is wrong?

AIngies list

well, that's about it for the thread I imagine :D

thanks

funny enough, there have been some huge problems involving congressman with both bathrooms and children in regards to moral diligence.

We offer MCP and then consume it with our in-app assistant to go from a non technical prompt to a series of what is essentially API calls they can automate for themselves for repetitive tasks or things that require a few screens to accomplish can be done from the assistant widget itself, etc.

Let's hear what non-default country invented pop-art in the 50s.

I agree with mostly all of this, but personally I wrote a toy LLM almost 5 years ago and while it never saw much use outside of boring my wife with a shitty command line demo with glee it did help me understand how they worked and how to apply them, played a lot with JAX and pytorch, ended up building a ghetto version of MCP and an LLM-Pool to proxy requests to my baby local models and so I didn't struggle to see the evolution of openrouter and MCP agentic workflows. The same way i'm really glad when I was younger I built a bad webserver by myself, a really painful SQLx type database, etc etc etc - none of these things led me to developing for Nginx or Oracle nor will knowing JAX get me a job at an AI research lab, but I do have a lot of depth in understanding how the technology works so that the flavors on top of them are easy to digest and make more use of immediately, and I think the same can be said for engineers coming into the field - if it's a spooky LLM box you aren't going to be squeezing the same amount of juice as the guy that knows how they work inside and out so having at least the understanding of a _babys first LLM_ is going to get you miles ahead of people who don't.

For anyone who wants to dork around there is https://github.com/rasbt/LLMs-from-scratch which is something amazing that I think anyone who wants to engineer things around LLMs should at least blast through and read.

I'm not worried about the volatility in the definition, i'm worried that I give it 1 token today and receive 2 token output, tomorrow I receive 40. If i'm doing this a hundred thousand times a day it is difficult to price this in for users downstream or in the extreme cases be able to absorb that at all short of going into a failmode with degraded access until someone goes and buys more tokens or gets the bill. The alternative is just pass the buck and bill your non-technical customers with a "tokens" line iteim every month.

I see. In my head it would be something like the agents harness having a list of services it interacts with, reaches out to service.com/agents.md for a fresh copy every so often and uses that to resolve the relevant tool calls.

there are roughly three of them and they all use the same pricing model. I am also not in the position to build a frontier model company these days.

Not specifically Anthropic but why are we allowing billing to take place in tokens that are nebulous and fully controlled by the operators who have no aligned incentives?

If I have a user input and then sanitize and inject that into a prompt to do something, I have no idea how much that is going to cost at all and no real way to measure this properly. A parallel example is digital ocean or aws, i can go and measure/limit my compute/fs/memory/startup times/etc and while it can be impossible to get down to the last flop of money allocated - i can run things on a real budget with real constraints, opposed to an LLM where I have to .. prerun a sanitized user prompt through a tokenizer and then ask an LLM to guess what it may do and give token consumption estimates and then act on those in any sane manner for the user?

Perhaps i'm missing something to do realistic and static rails on things but I don't see a serious way at scale to use the token billing model handling things requiring a users free text input short of having to go pander to VC money to throw money at it until someone else figures it out.

*to clarify my rambling... We should be billed and given controls based on resource usage itself and not an opaque token concept on top of not being able to spin any knobs that control it's resource usage.

How is distributing a markdown file the bottleneck?

this is awesome and I hope this gains some real steam, we're building everything in rust and locally if i'm watching youtube and running a build+tests and my vscodium starts running the analyzer at the same time I've seen my machine stutter out as it eats up the memory.

ha this is the first time i've seen this but honestly yes, if there was an accessible enough for a 4 year old OS to "explore" around in to find the applications I would be throwing it on the USB as I type

Yup! I have a line running from it to water one of our beds, it's been raining so it's about as muggy as it gets today.

We've been on and off with water service because of it, we've got a bit of rain the last few days but the resovoirs in Puerto Rico were looking real skinny last week. Nothing humbles you like coming inside from doing yard work in the August Caribbean sunshine to realize your shower isn't running. RIP to my tomatos.

As someone who is fully bootstrapped and not looking for funding, I may be oblivious but some of the numbers I see versus the products I see i'm wondering if I should not be using my own capital and see if asking nicely can get me 200 million dollars

i spent an hour the other week looking for my pine watch charger, this may inspire another 20 minutes digging around the house

Sorry that was meant for who you replied to, I was pointing out the difference in the application of ethics and a personal vs corporate level and that they aren't there to argue a contradictory moral opinion at the company they are there to make sure that the company can execute contracts in a way that abides by the legal ethics of where the are operating - raytheon and stopping war was just an example it applies to all companies and I think most people, myself included, have an incorrect assumption of what those departments are even there for in the first place.

They make sure that they are executing contracts in a way that doesn't break the ethics of the jurisdictions they are operating in, they aren't a bunch of naive people pleading for less war.

I really don't agree. I'm not hear to evangelize rust but by using enums from DB to templates and writing the code to make it consistent my experience with LLMs is infinitely better than golang for consistency and you have to include a lot more context to make golang work without issues whenever things are operating on chans or workgroups.

When I was getting a D&B number I missed their call I wasn't expecting because I wont answer unknowns and my phone blocks half the calls they think are spam anyway, then had to spend the better half of a week answering spam calls before finally getting what I needed.

I do think the frontier models and providers should be aiming to be as insanely accurate and precise for machine interfacing as possible, the rest of the world can build a zillion interfaces into it based on the context that they are actually being used in. That's what they are going to end up doing they just seem to all be trying to build a really great API _for the future_ and a really cool chat bot.

It has worked great but i've spent more time beating LLM output into parseable output than I have reading and appreciating the prose it sends when i'm asking it something about some snippets of code.