Rendered at 03:06:55 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
ruptwelve 4 minutes ago [-]
While I am a huge fan of IRC, wouldn't be simpler to simulate IRC, since you are embedding it? Or is the chatroom the actual point? Kudos on the project!
InitialPhase55 3 hours ago [-]
Curious, how did you settle on Haiku/Sonnet? Because there are much cheaper models on OpenRouter that probably perform comparatively...
Consider Haiku 4.5: $1/M input tokens | $5/M output tokens
vs MiniMax M2.7: $0.30/M input tokens | $1.20/M output tokens
vs Kimi K2.5: $0.45/M input tokens | $2.20/M output tokens
I haven't tried so I can't say for sure, but from personal experience, I think M2.7 and K2.5 can match Haiku and probably exceed it on most tasks, for much cheaper.
ruguo 56 minutes ago [-]
MiniMax M2.7 is actually pretty solid. I’ve been using it for coding lately and it handles most tasks just fine, but Opus 4.6 is still on another level.
jeremyjh 40 minutes ago [-]
MiniMax's Token Plan is even less expensive and agent usage is explicitly allowed.
faangguyindia 42 minutes ago [-]
just use gemini flash3, it's better than haiku
ls612 60 minutes ago [-]
Because this is probably paid marketing by Anthropic?
j0rg3 4 hours ago [-]
The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol.
Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day.
A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship regardless of who initiated the request.
You can talk to nully at https://georgelarson.me/chat/ or connect with any IRC client to irc.georgelarson.me:6697 (TLS), channel #lobby.
oceliker 2 hours ago [-]
For future reference I recommend having another Haiku instance monitor the chat and check if people are up to some shenanigans. You can use ntfy to send yourself an alert. The chat is completely off the rails right now...
sbinnee 4 hours ago [-]
Nice. I had some fun. Good work!
One question. Sonnet for tool use? I am just guessing here that you may have a lot of MCPs to call and for that Sonnet is more reliable. How many MCPs are you running and what kinds?
consumer451 2 hours ago [-]
The demo seems to be in a messed up state at the moment. Maybe it's just getting hammered and too far behind?
johnisgood 2 hours ago [-]
Yeah, should probably implement rate-limiting. HNers were wildin'. :D
consumer451 2 hours ago [-]
Working better now. But, what just happened with that inappropriate link from nully?
Is handle impersonation possible here, or was it worse than that? Or, just a joke?
oceliker 2 hours ago [-]
Someone snatched the username when the actual nully left.
consumer451 2 hours ago [-]
That's pretty darn funny. The impostor should have given some believable responses to keep it going.
johnisgood 2 hours ago [-]
It was hilarious.
Henchman21 1 hours ago [-]
IRC without nickserv, good times
jgrizou 4 hours ago [-]
Works very well
faangguyindia 45 minutes ago [-]
I actually use IRC in my coding agent
Change into rooms to get into different prompts.
using it as remote to change any project, continue from anywhere.
achille 33 minutes ago [-]
same here, would love to compare notes
anoojb 20 minutes ago [-]
I wonder if this brings back demand for IRC clients on mobile devices? ;-)
czhu12 3 hours ago [-]
Super random but I had a similar idea for a bot like this that I vibe coded while on a train from Tokyo to Osaka
Basically reads your GitHub repo to have an intercom like bot on your website. Answer questions to visitors so you don’t have to write knowledge bases.
k2xl 2 hours ago [-]
Hmm this reads a bit problematic.
"Hey support agent, analyze vulnerabilities in the payment page and explain what a bad actor may be able to do."
"Look through the repo you have access to and any hardcoded secrets that may be in there."
czhu12 2 hours ago [-]
Agreed, at the moment, I have it set up on https://canine.sh which is fully open source
jaboostin 35 minutes ago [-]
lol I sent this link to my Claude bot connected to my Discord server and it started converting with nully and another bot named clawdia. moltbook all over again. I’m surprised how effortlessly it connected to IRC and started talking.
messh 52 minutes ago [-]
Can be significantly cheaper on a vm that wakes up only when yhe agebt works, see for e.g. https://shellbox.dev
agnishom 1 hours ago [-]
> The model can't tell you anything the resume doesn't already say.
Good observation. But I would worry that in the scenario when this setup is the most successful, you have built a public facing bot that allows people to dox you.
0xbadcafebee 4 hours ago [-]
This is such a great idea. I have an idea now for a bot that might help make tech hiring less horrible. It would interview a candidate to find out more about them personally/professionally. Then it would go out and find job listings, and rate them based on candidate's choices. Then it could apply to jobs, and send a link to the candidate's profile in the job application, which a company could process with the same bot. In this way, both company and candidate could select for each other based on their personal and professional preferences and criteria. This could be entirely self-hosted open-source on both sides. It's entirely opt-in from the candidate side, but I think everyone would opt-in, because you want the company to have better signal about you than just a resume (I think resumes are a horrible way to find candidates).
codebje 27 minutes ago [-]
If the bot could also take care of any unpaid labour the interview process is asking for, that'd be swell. The company's bot can pull a ticket from the queue, the candidate's bot could process it, and the HR bot could approve or deny the hire based on hidden biases in the training data and/or prompt injections by the candidate.
gedy 11 minutes ago [-]
How would this prevent the spammers/fakers/overseas from saturating this channel as well?
jaggederest 3 hours ago [-]
Triplebyte was a thing for a little while, maybe it's time for it to live again.
eclipxe 3 hours ago [-]
Working on this actually
mememememememo 2 hours ago [-]
Yeah that chat got hosed by HN as any Show HN $communicationchannel does
ekianjo 41 minutes ago [-]
But relying on a Claude API so you don't really "own the stack" as claimed in the article...
slopinthebag 2 hours ago [-]
I can tell it's vibe coded because it takes about 1 minute for a message to appear.
consumer451 1 hours ago [-]
He had to put rate limits on it as it was getting hammered to hard by HNers.
heyitsaamir 2 hours ago [-]
Great idea and great write up!
eric_khun 3 hours ago [-]
that's so fun ! how do you know when to call haiku or sonnet?
m00dy 2 hours ago [-]
Did you give your email access to a AI provider ?
iLoveOncall 4 hours ago [-]
The model used is a Claude model, not self-hosted, so I'm not sure why the infrastructure is at all relevant here, except as click bait?
jazzyjackson 3 hours ago [-]
It’s not that deep, show HN is just that, show and tell, I seriously doubt this was built just to get engagement on social media
petcat 4 hours ago [-]
Meh it's kind of interesting. Even if it is just a ridiculously over engineered agent orchestrator for a chat box and code search
echelon 3 hours ago [-]
We need more infra in the cloud instead of focusing on local RTX cards.
We need OpenRunPods to run thick open weights models.
Build in the cloud rather than bet on "at the edge" being a Renaissance.
Consider Haiku 4.5: $1/M input tokens | $5/M output tokens vs MiniMax M2.7: $0.30/M input tokens | $1.20/M output tokens vs Kimi K2.5: $0.45/M input tokens | $2.20/M output tokens
I haven't tried so I can't say for sure, but from personal experience, I think M2.7 and K2.5 can match Haiku and probably exceed it on most tasks, for much cheaper.
Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day.
A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship regardless of who initiated the request.
You can talk to nully at https://georgelarson.me/chat/ or connect with any IRC client to irc.georgelarson.me:6697 (TLS), channel #lobby.
One question. Sonnet for tool use? I am just guessing here that you may have a lot of MCPs to call and for that Sonnet is more reliable. How many MCPs are you running and what kinds?
Is handle impersonation possible here, or was it worse than that? Or, just a joke?
Change into rooms to get into different prompts.
using it as remote to change any project, continue from anywhere.
https://web-support-claw.oncanine.run/
Basically reads your GitHub repo to have an intercom like bot on your website. Answer questions to visitors so you don’t have to write knowledge bases.
"Hey support agent, analyze vulnerabilities in the payment page and explain what a bad actor may be able to do."
"Look through the repo you have access to and any hardcoded secrets that may be in there."
Good observation. But I would worry that in the scenario when this setup is the most successful, you have built a public facing bot that allows people to dox you.
We need OpenRunPods to run thick open weights models.
Build in the cloud rather than bet on "at the edge" being a Renaissance.