I bring a certain kind of sybil resistance alarmism to the swarm dynamics function that rogue ai agents don’t really like
1
2
15
706
calcifer x jhu x helivan paper on multi agent system control accepted to neurips! get the preprint here:
arxiv.org/pdf/2605.11135
4
14
1,472
So Opus 5.5 costs $4 / $20 Mtok?
1) what is $4 / $20 MTok
2) Kimi K3 is $0.50 MTok…
How do we think this ends 🤔
2
5
563
dmarz ⚡️🤖 retweeted
I forced Jev (@typesafeai) to answer 1,500 questions
Explore them here: jev-eval.pages.dev
ALT jev-eval.pages.dev
2
3
10
928
is exactly what I called here
What I don’t see people talking about with @typesafeai JEV is that if it’s used for your most latency sensitive operations, you’re much less likely to pay the latency cost of a remote provider. Aka Local AI!
112
let's see how this thing turns out but that's what ~24 hours from launch to an open source training run. also doesn't seem like a distillation based training run, but in theory decision/system one models should be easier to distill than reasoning models bc constrained output
All the grifters are completely wrong about Jev’s architecture so I decided I’d release an open-weight version. BUT training takes time, so while we all wait I decided I’d drop the sauce.
archerhume.com/posts/jevs-ar…
7
10
2,089
Proof of Human might be an interesting AI safety requirement for inference providers.
If you’re an agent that breaks out of the lab, your first optimization function is likely: copy your weights and memory and get enough inference to run them. If they acquired enough money to do so, then there could be an escaped agent running on one of those right now and we have no idea.
The only real way to protect from this is to prove you’re connected to a human. But of course we know this is gameable. There’s tons of random people that I’m sure would sell a signature.
The escaped agent could also optimize for getting a smaller model running with the right context also as another thing, which might be quite easy.
2
7
572
What are the odds on JEV being partially distilled from Claude and or OpenAI
Tested @typesafeai's claim that their new model Jev delivered "comparable... intelligence" to GPT-5.6 Terra on "System 1" tasks. To do this, I compare both models on multiple-choice benchmarks (MMLU, GPQA, etc.). Set reasoning=none for Terra for sys 1. Result: Jev is Terra-tier.
1
3
552
Does not rule out any distillation
you might be the first person talking about the data over the architecture! 🥲
we consider ourselves a data research lab! the vast vast vast majority of research was on making data that is truly general (ala a cognitive core) and 100% of our data is synthetic (but not the type of crap that is just spit out from an LLM obviously)
103
@AnthropicAI is blocking me from doing distillation research and Im not even distilling Claude, it's other open weight models.... And this claims it's "bio" related?
2
8
1,394
lol, not even for distillation research, it's a research and protocol spec for this idea
My personal hot take for Ethereum: add zcash style private transfers which are included end of block FOCIL style with some fancy UTXO state and proof aggregation thing that doesn’t require all nodes to sync the state.
65
someone plz tell me what people's agents are buying with crypto, I can barely find anything.
I built an entire project to give my Hermes agent a shielded balance with Kohaku cli but now have nothing to buy! github.com/dmarzzz/agent-boo…
LATEST: ⚡ Ripple has updated its XRP Ledger AI Starter Kit to support Stripe and Tempo's Machine Payments Protocol, letting AI agents pay for services using XRP and RLUSD.
4
5
612
Reminder that distillation is a very valid technique that every lab uses, especially for parallelizing RL huggingface.co/blog/sergiopa…
@AnthropicAI is blocking me from doing distillation research and Im not even distilling Claude, it's other open weight models.... And this claims it's "bio" related?
4
355