Jason certainly does [1]. The commercial bots seamlessly traverse between AI, auto-respond and human.
It's very much an ensemble method. That's why people pay for it over just downloading an abliterated model from hf with system prompt hacking. Go and try it, the SOTA of role-playing models still have a lot to be desired
> The commercial bots seamlessly traverse between AI, auto-respond and human. It's very much an ensemble method.
This seems unlikely to me, given it'd increase costs and the response times would make it obvious.
The messages presented in the original source appear to be people expecting to be talking to a real person, likely on a dating app. The relation to AI is only speculative, and mostly in the direction of "my messages may be used to train a chatbot to replace my job of deceiving people" - which is plausible.
> That's why people pay for it over just downloading an abliterated model from hf with system prompt hacking.
I'd assume convenience, fine-tuning, and using a larger model than it's feasible for most people to run locally.
I don't see the news here ... there's https://huggingface.co/collections/microsoft/bitnet which is last updated 12/2025 ... am I just paying more attention here or is there something actually new about this?
Also as far as I know, this is more of a research curiosity - BitNet really doesn't perform that well on evals.
I think Qwen3.5 2B is the best you can get in the ~1GB class.
The best way to protect children is to educate them to protect themselves, but that argument generally falls on deaf ears, doubly so when there's an opportunity to use "but the children" as a political cudgel.
While I think you and I would agree if I argued it was more about culture than firearms per-capita, it's pretty hard to say children aren't suffering some pretty real harms from said firearms (to say nothing of adult suicide statistics when firearms are kept in the house)
Reducing the number of guns doesn't solve the root issue (which I think we'd also agree on), but it should minimize the harms while being dramatically easier than changing the American ethos. Hell, America could likely get 80% of the results (no school shootings) with 20% of the effort (additional restrictions on firearms, more akin to Canada)
I further think the second amendment is causing Americans more harm than it's worth, though that's a seperate discussion; some examples include suicide statistics, accidental discharge, a lack of protection even when carried legally (such as in Alex Pretti's murder) and the fact that, when firearms could be anywhere, police must treat every interaction as potentially fatal - with all the force that requires
whats incredible to me are how many useful idiots out there STILL fall for it.
___ said hamas beaheaded 40 babies and that turned out to be a complete fabrication. That fake info was used in part to justify killing thousands of kids in ____
meanwhile the recent strike on Iran resulted in 80 little girls getting killed (with plenty of evidence) and its swept under the rug while we get blasted about the 7 soldiers that died.
More useful idiots are born every day, most of them never are educated and do not see their past blunders as anything wrong happening, they are completely blind to the real implication of their actions.
I know some idiots that read newspapers and technical papers and yet would rather have company like discord providing safety for their new born daughter but would vote for small govt republicans (or democrats, i don't care, it's just a label that is applicable now. they are mostly all the same) and do nothing about calling out the actual child predators and taking proper action against them. It is bonkers
The intention is to get this working better and then provide it as a free api and also post the entire qdrant database (or whatever is eventually used) for off-line use.
This will pair with something called a "credential file" which will be a [key, repo] pair. There's an attack vector if you don't pair them up. (You could have an mcp server for some niche thing, get on the aggregators, get fake stars, change the the code to be to a fraud version of a popular mcp server, harvest real api keys from sloppy tooling and MitM)
Anyway, we're talking about 1000s of documents at the most, maybe 10,000. So it's entirely givable away as free.
If you like this project, please tell me. Your encouragement means a lot to me!
I don't want to spend my time on things that nobody seems to be interested in.
> If you like this project, please tell me. Your encouragement means a lot to me! I don't want to spend my time on things that nobody seems to be interested in.
Great implementation details, but what is the end goal? Ah ha, a readable readme (which itself is promising):
InfiniteMCP is a an MCP server that acts as a universal gateway to thousands of other MCP servers. Instead of manually configuring each MCP server you want to use, InfiniteMCP lets Claude discover, understand, and use any MCP server on demand through natural language queries.
Think of it as an "MCP server of MCP servers" - a single connection that unlocks the entire MCP ecosystem.
So, yeah, that's interesting.
> and then provide it as a free api
Oh, oops, that just became a supply chain threat. Central registries outside of targets' control are grails, and the speculated implementation for secrets makes this a lovely injection path...
If you pursue this, work with someone like control-plane.io to blue/red team it and make noise about that on your README with a link to their findings and your mitigations. And consider sync up with folks like kusari.dev (see also SLSA and GUAC) to include a vulns rating on each MCP itself (their mapping is super fast and a SBOM scanned MCP directory would be a real value add).
Essentially I've cloned thousands of mcp servers, used the readmes and the star rating to respond to the qdrant query (star ratings as a boost score have been an attack vector, yes I know, it's an incomplete product [1]), then presents it as a JSON response with "one-shots" which this author calls clis.
I think I became discouraged from working on it and moved on because my results weren't that great but search is hard and I shouldn't give up.
I'll get back on it seeing how good this tool is getting traction.
[1] There needs to be a legitimacy post-filter so that github user micr0s0ft or what-have-you doesn't go to to the top - I'm sure there's some best-of-practice ways of doing this and I shouldn't invent my own (which would involve seeing if the repo appears on non-UGC sites I guess?!) but I haven't looked into it
here's coming from markdown
reply