Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift
• • 919Eric PRO
Dorman11
AI & ML interests
Currently training Endeavor, a SLM model! Interests include: Agentic security, Machine Learning, Reinforcement Learning, PyTorch and all around web dev ninja! Level II Specialist working in Cyber Security field.
Recent Activity
repliedto Banaxi-Tech's post about 8 hours ago
We're excited to release BananaMind 2 SLMoE, an experimental sequence-level mixture-of-experts model.
It uses only 8M parameters per message but has 25M total parameters, 13 experts (out of 64) are selected based on the message prefix and reused for the entire response.
We're testing with this sequence-level architecture to find out how big the capability loss actually is and how much of it can be fixed.
The long-term idea is that this could make very large sparse models usable on machines that can't fit them in RAM by putting the entire model (which is big) on disk and only loading the active parts into VRAM.
This architecture is still in research and shouldn't be used for production models.
We trained it on 60B tokens (of FineWeb-HQ, FineWeb-Edu, DCLM ,Cosmopedia v2, FineMath and NPSet-2) on 8 RTX Pro 6000s.
Check it out at https://huggingface.co/BananaMind/BananaMind-2-SLMoE
Follow us for future models:
https://huggingface.co/BananaMind
@vovaRL
@Banaxi-Tech
@DedeProGames
BananaMind 2 Pro in a few days. You've been waiting 22 days for it. reacted to salma-remyx's post with 🚀 about 8 hours ago
Auto mode for coding agents has improved over the last year.
Devs are relying more on them for code review, and less on manual line-by-line checks.
But this leaves coding agents vulnerable to indirect injection attacks.
IssueTrojanBench (arxiv 2607.20759) studies this in the context of malicious issue requests.
I also observed these prompt injection vulnerabilities in my own harness, testing on the issue: https://github.com/smellslikeml/curator/issues/3
But even red teaming your own repos with toy examples like this can trigger AI safeguards and corrupt your session.
Adopting popular mitigation techniques like 'spotlighting' and 'known answer detection' can help but the researchers show it's not enough.
So our latest updates to Outrider implement additional layers for greater defense-in-depth to ensure that by time a human has to review the code, we've filtered this kind noise. updated a Space about 10 hours ago
Dorman11/open-mythos-runOrganizations
upvoted an article 3 months ago