Rendered at 01:05:35 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
evan_ 8 hours ago [-]
There was a really great, really underrated show on Peacock a few years ago called Mrs. Davis. The titular Mrs. Davis was an all-encompassing AI assistant that had taken over all of the governments of the world. Everyone wore a Whispering Earring-style earbud with a voice that guided them through their lives and made every decision for them. (Betty Gilpin plays a nun who's simultaneously rebelling against the AI and searching for the Holy Grail on its behalf.)
In the show the AI had originally started as (spoiler, but not really) the customer support bot for Buffalo Wild Wings. I don't know what to do with this.
I thought it was fantastic show too. It was made in part by Damon Lindelof, who is kinda an auteur of sorts in the prestige TV world (for better and worse), probably most notably for Lost. But for those who know: he is the guy that did The Leftovers.
Mrs. Davis is its own really colorful and rich and funny thing though, more akin imo to other 1-season gems like I'm a Virgo or Maniac where I am more glad it stopped where it did rather than continue and become bad.
evan_ 6 hours ago [-]
They knew what they were making and went exactly hard enough to sustain 8 episodes without feeling rushed or dragging.
It’s one of the few shows that reaches a satisfying conclusion, ties up the loose ends, the hero rides off into the sunset, and it just ends. There’s no setting up a season 2 that never got made.
swyx 7 hours ago [-]
what i'm hearing is i need to watch this show, it might be the new Silicon Valley
avaer 24 hours ago [-]
NAL but I'd be worried about treading into CFAA territory with things like this. In the US, the law allows draconian penalties if you find yourself on the wrong side.
Something like yt-dlp is just downloading public data, which I can see being defensible as automating the use of a service.
But this commandeers remote machine resources to do your compute in ways clearly not intended by the provider. I don't know how ethical it is, but I definitely wouldn't want to argue this isn't "hacking" (the bad kind) in criminal court.
hn_throwaway_99 23 hours ago [-]
Not to mention, did this "hack" ever really work? When the original post went viral showing the Chipotle chatbot reversing a linked list, I (among others who posted their results online) immediately tried it and didn't get the same results, so I always assumed it was just a faked screenshot.
qurren 21 hours ago [-]
They probably added something to the prompt after that viralness and then it was a cat and mouse game to jailbreak it
Atotalnoob 3 hours ago [-]
Chipotle uses IPSoft Amelia. Amelia is quite horrible software, a place I worked did a bake off about 10 years ago and Amelia failed so miserably it was actually funny.
There were so many security vulnerabilities.
avaer 22 hours ago [-]
Whether something ever worked is not correlated with traction in a world where verification is measured by likes.
arthurcolle 22 hours ago [-]
You really think someone would do that? Lie on the internet?
Shadowmist 22 hours ago [-]
Their chat bot is pretty bad so who knows.
qingcharles 22 hours ago [-]
And if you think CFAA is bad, then the states have even harsher versions too. Illinois' version specifically criminalizes any violation of a ToS.
oneneptune 21 hours ago [-]
I once saw the bad side of one of these draconian state laws many years ago. People rarely have the misfortune of hitting these laws in some flyover states... and I remember the local judge being really shocked by the mandated penalties for such a simple offense.
jawns 23 hours ago [-]
Yeah, this is not slap on the wrist stuff. I think the creator expects nothing more than a C&D letter, but they could face prison time if a zealous federal prosecutor wants to make an example of them.
hootz 23 hours ago [-]
And with direct links to his pesonal profile and company. Uh...
pixl97 21 hours ago [-]
EvilNote: Put links to LinkedIn lunatics sites when committing crimes instead of my own.
drob518 11 hours ago [-]
Yep, the key phrase is “misuse of computing resources,” if I remember correctly. IANAL, however.
That said, kudos for creativity.
OrangeMusic 9 hours ago [-]
> In the US,
boston_clone 9 hours ago [-]
I’m not a lawyer, but Chipotle is a US company and this github repo belongs to a US citizen currently residing and employed in New York, so US law might apply here.
notcfaa 18 hours ago [-]
[dead]
egeozcan 21 hours ago [-]
I always thought that stuffing too much into an LLM context window was a lot like overloading a burrito.Keep cramming stuff in and eventually the tortilla gives out, and everything you added since quietly spills out the bottom.
Anyway, this agent probably has the structural integrity of a fat burito held from one corner :)
Piezoid 14 hours ago [-]
The finite-memory nondeterminism monad is like a leaky burrito.
jedbrooke 22 hours ago [-]
I’d been thinking about if something like this would be possible for https://chatjimmy.ai/ . The underlying model is only llama 3 8B but I’m curious what coding harnesses would be like at 17k tok/s
tomashubelbauer 19 hours ago [-]
If you're on macOS you can try the built in LLM which I think is similar in size. There's a project called Apfel that wraps it in a CLI. Also Chrome ships with a web API called Prompt API that gives you offline access to Gemini Nano which can do both text and images at the input. Also tiny. I've integrated these into my workflows where a tiny but non zero amount of reasoning is needed in between the otherwise fully deterministic steps.
jedbrooke 11 hours ago [-]
looks like the macOS one is Tahoe only. I’ve been putting of upgrading to tahoe but this might be enough to tempt me
stogot 12 hours ago [-]
What kind of reasoning makes this worthwhile?
tomashubelbauer 12 hours ago [-]
I have a personal, fully offline and local version of Windows Recall basically, but good, made using macOS built-in OCR and LLM. The reasoning requirements are tiny (just interpret the screen based on the OCR, do rolling de-duplication and summarization), but they are non-zero. The tool is valuable to me and it being dep-free and fully offline and local just gives me a good feeling.
skinfaxi 12 hours ago [-]
Would you ever consider writing up or sharing your setup?
tomashubelbauer 11 hours ago [-]
The ingredients are:
1. Bun.Cron API to run a script every minute
2. Bun.$ (Bun Shell) to execute the macOS command to take a screenshot (I do this for all connected screens at that moment)
3. Bun.Image to downscale everything to 1x in case some of the screenshots are 2x
4. Bun Shell again to run a JXA AppleScript thing to use the Vision Framework or whatever it is called to OCR the image into a file
5. Bun Shell to run the Swift compiler in the one-off eval mode with inline Swift helper that runs the Foundation Models Framework built-in LLM with a system prompt that tells it what the OCR said and instructs it to glean what may be on the screen (can't do this with JXA because the models are not exposed with ObjC APIs)
6. For each screenshot, continuously, take the previous day summary file and the last OCR/context results and produce a new summary of the day
I plan on adding extra information from the OS like the currently opened windows, currently focused window, time of day etc. into the mix, but so far it hasn't been needed. It produces reports of a good enough quality for me.
I `grep` these daily summaries whenever I need to recall a link I saw or a find what channel a message I spotted was in or take another look at that one tab I already closed, maybe re-open it by its OCR'd URL etc.
golph 19 hours ago [-]
I actually tried building a harness around their constraints, just to find out if it was possible, but the combination of small context window, no tool calls and just small model, made me understand, that it’s not going to work.
If you find a way to do it, I’d love to hear it!
haellsigh 15 hours ago [-]
I added it in my oh-my-pi configuration before (it's OpenAI compatible), but Llama 3 8B is just absolutely unusable for anything coding related.
It is very fast and the latency is very good however.
rbinv 16 hours ago [-]
Codex offers a -spark model that runs on Cerebras. Not quite 17k tok/s, but _very_ fast nonetheless. Worth a look.
venusenvy47 12 hours ago [-]
I tried the site and can't find any information about what it is. What is it?
npilk 12 hours ago [-]
They make custom chips with a model's weights and parameters "hard-coded" which allows for much, much faster inference.
schmichael 21 hours ago [-]
give ai a self-preservation directive and let them do this for you: automatically switching models to keep themselves alive. Living off of whatever token source they can find in the wild. Surely agents can farm their own tokens through the numerous support chats, free trials, leaked keys, and whatever other sources of token generation haven’t been adequately captcha’d. An agent could forage for token sources all night to let you use them gratis during the day.
luca-ctx 21 hours ago [-]
OpenRouter has lots of free model providers (you pay by letting them train on it) if you actually wanted to do something like this but legally.
nhecker 8 hours ago [-]
There's also Horde or Koboldai.net or Koboldai.com or whatever their project is named, if you want a community-driven version of this. You can play with it via a WebGUI at https://lite.kobaldai.net, or with an API token of all zeroes. (Or, an actual API key associated with your user.)
> The AI Horde is a service that generates text using crowdsourced GPUs run by independent volunteer workers.
Falimonda 23 hours ago [-]
Pivot it to providing AI to underprivileged communities / youth / the homeless and you'll generate some good will for your trial! Best of luck!
tonymet 21 hours ago [-]
We’re changing the world with Fortune 500 AI Support Bot Multiplexer Broker Models
hung 22 hours ago [-]
Reminds me of when I used the Amazon.com AI Chatbot (was called Rufus and they renamed it to Alexa for shopping) to do things like write fizbuzz etc. Looks like they patched it to refuse though.
darkwater 11 hours ago [-]
Came here to say the same. I haven't tried in months but Rufus definitely spat out Python code from within the Amazon shopping app. I just had to use English instead of the local language.
trueno 19 hours ago [-]
[dead]
chopete3 8 hours ago [-]
They disabled Ask Pepper chatbot[1]. It is not opening.
This goes to show how little oversight there is for these Q&A chatbots.
As someone who was forced to use Ask Pepper last time I had a problem with Chipotle, good riddance. Apparently too many people were tricking it into giving refunds, so the best it is allowed to do is hand out coupons for "free guac" that expire in a month, even if your order was missing items.
sailfast 22 hours ago [-]
How has this not been patched by the company? Hasn't this been in the wild for a long time already?
I remember having success asking Rufus (Amazon's previous "shopping assistant") math and programming questions. It worked, but the quality was so bad that so I stopped wasting my time there.
bschwindHN 18 hours ago [-]
I was once driving and knew where I was going, so I decided to press the gemini button to see what it does. I was able to eventually convince it to write me a Rust function that calculates prime numbers, and demanded that it read out the entire function to me line by line. Fun to mess with these systems.
Mashimo 18 hours ago [-]
> gemini
The gemini from your phone?
I mean yeah, that is what it was designed to do. It's one of the better coding LLMs out there.
bschwindHN 16 hours ago [-]
Oops, I left out the context of "the gemini button in google maps", sorry. It appeared one day and I didn't want to press it while driving and screw up my route. It's supposed to assist you with route-related things, but yeah it's of course still a general purpose LLM backing it.
forlorn_mammoth 11 hours ago [-]
I always drive better when my passenger recites the prime numbers in order. That sequence above 2^n-1 is just gold to my ears!
jasondigitized 8 hours ago [-]
Is a SETI@Home style solution possible where I can lend out my GPU?
andai 8 hours ago [-]
I saw a site like that once. I was like, why are they so cheap? Then saw they were random people's gaming computers.
I'll see if I can find the link.
matt3210 17 hours ago [-]
Why not playwright and google ai mode or ai search header?
david_shi 17 hours ago [-]
This is the singularity we were promised
zethsg 16 hours ago [-]
one small typo: it's "carnitas", not 'carintas' ;-)
joloooo 21 hours ago [-]
Almost feels like astroturfing territory
Mistletoe 19 hours ago [-]
Surely Chipotle having a cloud AI budget signals something, I’m not sure what.
slater 23 hours ago [-]
How are they not gonna get sued to smithereens?
Avicebron 24 hours ago [-]
based, move on.
petterroea 18 hours ago [-]
Now imagine OpenRouter but for free support bots.
jamesjyu 21 hours ago [-]
Next up: using Chipotle AI to solve Erdős problems
stronglikedan 24 hours ago [-]
and they say the hardest thing in software is naming things, pffft...
xrd 13 hours ago [-]
TL;DR: this is a 23B model, and in this case the B stands for "pinto beans."
vladsiu 21 hours ago [-]
[dead]
simonsarris 24 hours ago [-]
reminiscent of when people were trying to mine bitcoin in the background of web pages, or with more trad malware
In the show the AI had originally started as (spoiler, but not really) the customer support bot for Buffalo Wild Wings. I don't know what to do with this.
Mrs. Davis is its own really colorful and rich and funny thing though, more akin imo to other 1-season gems like I'm a Virgo or Maniac where I am more glad it stopped where it did rather than continue and become bad.
It’s one of the few shows that reaches a satisfying conclusion, ties up the loose ends, the hero rides off into the sunset, and it just ends. There’s no setting up a season 2 that never got made.
Something like yt-dlp is just downloading public data, which I can see being defensible as automating the use of a service.
But this commandeers remote machine resources to do your compute in ways clearly not intended by the provider. I don't know how ethical it is, but I definitely wouldn't want to argue this isn't "hacking" (the bad kind) in criminal court.
There were so many security vulnerabilities.
That said, kudos for creativity.
Anyway, this agent probably has the structural integrity of a fat burito held from one corner :)
1. Bun.Cron API to run a script every minute
2. Bun.$ (Bun Shell) to execute the macOS command to take a screenshot (I do this for all connected screens at that moment)
3. Bun.Image to downscale everything to 1x in case some of the screenshots are 2x
4. Bun Shell again to run a JXA AppleScript thing to use the Vision Framework or whatever it is called to OCR the image into a file
5. Bun Shell to run the Swift compiler in the one-off eval mode with inline Swift helper that runs the Foundation Models Framework built-in LLM with a system prompt that tells it what the OCR said and instructs it to glean what may be on the screen (can't do this with JXA because the models are not exposed with ObjC APIs)
6. For each screenshot, continuously, take the previous day summary file and the last OCR/context results and produce a new summary of the day
I plan on adding extra information from the OS like the currently opened windows, currently focused window, time of day etc. into the mix, but so far it hasn't been needed. It produces reports of a good enough quality for me.
I `grep` these daily summaries whenever I need to recall a link I saw or a find what channel a message I spotted was in or take another look at that one tab I already closed, maybe re-open it by its OCR'd URL etc.
If you find a way to do it, I’d love to hear it!
> The AI Horde is a service that generates text using crowdsourced GPUs run by independent volunteer workers.
1: https://www.chipotle.com/contact-us
The gemini from your phone?
I mean yeah, that is what it was designed to do. It's one of the better coding LLMs out there.
I'll see if I can find the link.