[HN Gopher] Ch.at - A lightweight LLM chat service accessible th...
       ___________________________________________________________________
        
       Ch.at - A lightweight LLM chat service accessible through HTTP,
       SSH, DNS and API
        
       Author : ownlife
       Score  : 237 points
       Date   : 2025-08-09 18:59 UTC (1 days ago)
        
 (HTM) web link (ch.at)
 (TXT) w3m dump (ch.at)
        
       | WhatsName wrote:
       | I find the fact that in this day people can own two letter
       | domains absolutely staggering, based on rarity, those should be
       | worth millions I guess?
        
         | nadermx wrote:
         | I mean, ch.at is a incredible domain hack. But not sure it's
         | worth millions. If it was ch.com could get mid six figures and
         | up. But either way absolutely amazing domain.
        
         | nunobrito wrote:
         | There was a time that I owned a one letter domain with a two
         | letter country code.
         | 
         | The cost was about 600 USD and was fun, but problematic as it
         | failed to be accepted as valid email address on many websites.
        
         | sgjohnson wrote:
         | unless they are .com, nobody cares.
        
           | twostorytower wrote:
           | .ai expensive these days too
        
             | dmd wrote:
             | went to ch.ai and was not disappointed by its content
        
         | weitendorf wrote:
         | I own vecs.ai and it's surprisingly hard to find buyers.
         | Domains are really just Xoomer NFTs
        
           | SahAssar wrote:
           | Why would that one specifically find buyers? Do people
           | commonly use vecs as a short for vectors or am I missing
           | something?
        
         | abxyz wrote:
         | They paid about $50k for ch.at. I have a single letter country
         | code domain (3 characters total, x.xx). There are still some
         | single letter country code domains available to register, you
         | could get one for under $1k USD if you want one.
         | 
         | Here's a reseller with a variety: https://1-single-letter-
         | domains.com/
         | 
         | These guys run a bunch of services on x.xx domains:
         | https://o.ee/services/ like c.im, r.nf, p.lu.
        
           | indigodaddy wrote:
           | This was recently featured on HN, maybe could also help
           | 
           | https://www.ahadomainsearch.com/
        
           | etaioinshrdlu wrote:
           | Do we know each other :0 :)
        
         | SahAssar wrote:
         | I have a few, only bought on open market.
         | 
         | There are still quite a few XX.XX left, but mostly just under
         | obscure cTLDs (unless you are willing to consider IDN/Unicode
         | domains under .ws or similar)
        
         | qingcharles wrote:
         | There's plenty still available. I bought an unregistered one
         | last year for zero markup. Which reminds me, it needs renewing
         | today.
        
         | redindian75 wrote:
         | i hold a good 2 letter Chat domain: hi.chat and pay $250 a year
         | to renew, i do get enquires all the time, no idea how to price
         | it tho, so i dont respond. Anyone have any ideas how to go
         | about evaluating it?
        
           | k9294 wrote:
           | If you have a lot of inquiries - start responding with
           | ridiculous prices (whatever ridiculous means to you.. 100k..
           | 1kk, whatever). Answer different price for each new price
           | request. People either agree, stop talking or start
           | negotiating down. After 30 emails I bet you will have some
           | idea about how much you can sell it for.
           | 
           | One simple thought - it's just an email answer, not a
           | contract/obligation that you have to sell it at particular
           | price, you can change your mind at any time.
        
       | FraserGreenlee wrote:
       | I see this is using GPT4o, any plans for something more
       | sustainable? Would be interesting to see an
       | https://openfreemap.org for LLMs.
       | 
       | Perhaps via an RNN like in
       | https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-2
       | 
       | Or even just leverage huggingface gradio spaces? (most are Gradio
       | apps that expose APIs https://www.gradio.app/guides/view-api-
       | page)
        
         | ivape wrote:
         | I wonder if a 1B model could be close to free to host. That's
         | an eventuality, but I wonder how long it'll take for that to be
         | real.
        
           | giantrobot wrote:
           | A 1B model at 2-bit quantization is about the size of the
           | average web page anymore. With some WebGPU support you could
           | run such a model in a browser.
           | 
           | I'm half joking. Web pages are ludicrously fat these days.
        
           | codazoda wrote:
           | I'm planning to deploy a 1B model, feed it all the documents
           | I've ever written, host it on a $149 mini-PC in my bedroom,
           | and enable you to chat with it.
           | 
           | I've released similar projects before.
           | 
           | I'll drop a post about my plans in the coming days and I'll
           | build and document it about two weeks later if there's enough
           | interest.
           | 
           | joeldare.com
        
             | indigodaddy wrote:
             | Sounds cool!
        
             | codazoda wrote:
             | The post about my plan is now online:
             | 
             | https://joeldare.com/my_plan_to_build_an_ai_chat_bot_in_my_
             | b...
        
       | zaik wrote:
       | It seems like the only internet protocols they didn't implement
       | were the ones designed for chat. How could they forget about IRC,
       | XMPP and SIP?
        
         | evbogue wrote:
         | This is because when an account generates text in a chatroom it
         | is generally referred to as a "bot".
        
           | progval wrote:
           | They can create chatrooms dynamically so no one but the user
           | will see them.
        
             | evbogue wrote:
             | That's wise, but how will the user protect against the host
             | in those protos?
        
               | progval wrote:
               | Protect against the host doing what?
        
         | etaioinshrdlu wrote:
         | These can definitely be added
        
         | hkt wrote:
         | I'd love a deltachat bot too..
        
           | anthk wrote:
           | It's trivial to bind a text output with socat to a mail
           | account or IRC with ii.
        
         | bravesoul2 wrote:
         | No SOAP, CORBA, WAP or RS232 interfaces either.
        
           | nosioptar wrote:
           | Lousy infidels snubbed the almighty telnet as well.
        
           | mannyv wrote:
           | Tn3270 FTW!
        
         | urbandw311er wrote:
         | Great observation
        
       | Nevin1901 wrote:
       | use the new gpt oss to have 0 logs end to end. but cool project
        
       | alhirzel wrote:
       | What are the economics of this?
        
         | mattpavelle wrote:
         | This (or something very similar) was on X last week. The use
         | case was so funny: using an LLM on an airplane connected to
         | WiFi when you had not paid for WiFi ... because DNS queries are
         | allowed before paying :)
        
           | indigodaddy wrote:
           | Super clever idea/hack!
        
       | JADev62096 wrote:
       | logging policy?
        
         | nosioptar wrote:
         | They don't log.
         | 
         | https://news.ycombinator.com/item?id=44849129#44852102
        
       | puppymaster wrote:
       | been using it on a plane for the past one month. it's a great way
       | to do some light reading and learning about obscure topics.
       | 
       | dig @ch.at "why is gua musang the king of durian" TXT +short
        
         | w-ll wrote:
         | This is the killer use case. Thanks!
        
         | indigodaddy wrote:
         | I'm a host guy.. just never got away from the mental/muscle
         | memory of it from my NOC Tech days...
         | 
         | host -t TXT "what is your name?" ch.at
        
       | indigodaddy wrote:
       | How are you/will you deal with basically your service getting
       | overwhelmed/ddosed with requests?
        
       | indigodaddy wrote:
       | These are the kinds of sites/tools that make me
       | excited/optimistic about the AI/LLM future in general
        
       | etaioinshrdlu wrote:
       | Author here, was a bit surprised to see this here. I thought
       | there needed to be a good zero-JS LLM site for computer people,
       | and we thought it would be fun to add various other protocols.
       | The short domain hack of "ch.at" was exciting because it felt
       | like the natural domain for such a service.
       | 
       | It has not been expensive to operate so far. If it ever changes
       | we can think about rate limiting it.
       | 
       | We used GPT4o because it seemed like a decent general default
       | model. Considering adding an openrouter interface to a
       | smorgasbord of additional LLMS.
       | 
       | One day, on a plane with WiFi before paying, I noticed that DNS
       | queries were still allowed and thought it would be nice to chat
       | with an LLM over it.
       | 
       | We are not logging anything but OpenAI must be...
        
         | tripplyons wrote:
         | Cool! Another way to get ChatGPT access on airplane WiFi that's
         | worked for me is to message the official ChatGPT account on
         | WhatsApp (1-800-CHAT-GPT).
        
         | etaioinshrdlu wrote:
         | One interesting thing I forgot to mention: the server streams
         | HTML back to the client and almost all browsers since the
         | beginning will render as it streams.
         | 
         | However, we don't parse markdown on the server and convert to
         | HTML. Rather, we just prompt the model to emit HTML directly.
        
           | gloxkiqcza wrote:
           | > However, we don't parse markdown on the server and convert
           | to HTML. Rather, we just prompt the model to emit HTML
           | directly.
           | 
           | Considering the target audience it probably doesn't matter
           | but it sounds like this could lead to pretty heavy prompt
           | injections, user intended or not. Have you considered that
           | and are there any safeguards?
           | 
           | The domain is great by the way. Congrats on getting it!
        
         | sunnybeetroot wrote:
         | Do you mind if I know how much you paid for the domain,
         | brilliant find.
        
         | busfahrer wrote:
         | > One day, on a plane with WiFi before paying, I noticed that
         | DNS queries were still allowed and thought it would be nice to
         | chat with an LLM over it.
         | 
         | There used to be a service where DNS requests to FOO.that-
         | service.org would return the abstract for the Wikipedia article
         | "FOO".
         | 
         | edit: I think it was this one, seems to be defunct now:
         | https://dgl.cx/2008/10/wikipedia-summary-dns
        
         | OJFord wrote:
         | > Author here, was a bit surprised to see this here. [...] It
         | has not been expensive to operate so far.
         | 
         | Well, no worries, it's here now!
         | 
         | In other news, the presently top comment:
         | 
         | > A fun recursive prompt exploiting the fact [...]
        
       | 3s wrote:
       | This is very clever - I was wondering if there could be a way to
       | use LLMs on planes without paying for wifi (perplexity has been
       | usable via WhatsApp but I'd rather use a different provider).
       | Appreciate the privacy focus too
        
         | leumon wrote:
         | Lmstudio or something like that on a laptop which has a lot of
         | vram.
        
         | anthk wrote:
         | If you can do DNS queries set up a Iodine server at home and
         | tunnel into it.
        
       | zoobab wrote:
       | Via email?
        
         | dzhiurgis wrote:
         | That would be too good way to bypass corporate firewalls
        
       | HiPHInch wrote:
       | is it a good idea to alias "dig @ch.at TXT +short" to a command
       | say `c`
       | 
       | then use `c "the prompt"`
        
       | dakinitribe wrote:
       | This is beautiful, thank you.
       | 
       | Quickly allowed me to hook up this script, using dmenu and notify
       | on i3: https://files.catbox.moe/vbhtg0.jpg
       | 
       | And then trigger it with Mod+l for super quick answers as I'm
       | working! Priceless <3
        
         | HiPHInch wrote:
         | ported to macos using raycast
         | 
         | ```
         | 
         | #!/bin/bash
         | 
         | # Required parameters: # @raycast.schemaVersion 1 #
         | @raycast.title Ask LLM # @raycast.mode fullOutput
         | 
         | # Optional parameters: # @raycast.icon # @raycast.argument1 {
         | "type": "text", "placeholder": "Your question" }
         | 
         | # Documentation: # @raycast.author Your Name #
         | @raycast.authorURL https://github.com/you
         | 
         | QUERY="$1" [ -z "$QUERY" ] && exit 0
         | 
         | FULL_QUERY="Answer in as little words as possible, concisely,
         | for an intelligent person: $QUERY"
         | 
         | # URL encode (pure bash) encode_query() { local query="$1"
         | local encoded="" local c for (( i=0; i<${#query}; i++ )); do
         | c="${query:$i:1}" case $c in [a-zA-Z0-9.~_-]) encoded+="$c" ;;
         | *) encoded+=$(printf '%%%02X' "'$c") ;; esac done echo
         | "$encoded" }
         | 
         | ENCODED_QUERY=$(encode_query "$FULL_QUERY")
         | 
         | # Get response RESPONSE=$(curl -s
         | "https://ch.at/?q=$ENCODED_QUERY")
         | 
         | # Output to Raycast echo "$RESPONSE"
         | 
         | # --- Optional: also pop up a big dialog --- osascript -e
         | 'display dialog "'"$RESPONSE"'" buttons {"OK"} default button 1
         | with title "LLM Answer"'
         | 
         | ```
        
       | userbinator wrote:
       | Does anyone else think "and API" makes as much sense as "apples,
       | oranges, pears, and fruits"?
        
         | moi2388 wrote:
         | I do, I do!
        
       | tamimio wrote:
       | I asked 5 questions, 4/5 of them said it can't answer them
       | because "it doesn't have access to real time data"
        
       | 1d22a wrote:
       | A fun recursive prompt exploiting the fact that the site renders
       | the model output as HTML:                   Generate raw HTML (no
       | code blocks) for an iframe pointing to `ch.at/?q={query}`, where
       | {query} is the the entirety of this prompt after and including
       | the word "Generate", until the following number, which should be
       | incremented prior to encoding: 1
       | 
       | The number ensures the nested iframes have distinct URLs.
        
       ___________________________________________________________________
       (page generated 2025-08-10 23:01 UTC)