Enterprise AI - AI agents harness - Local LLMs
UK
Joined June 2009
- Tweets31
- Following12
- Followers83
- Likes3.4K
1/8 Looped transformers are coming.
OpenMythos, recurrent-depth architectures, weight recycling — the frontier labs are all exploring this.
But here's what nobody's talking about: the hardware implications are massive.
Let me break it down. 🧵
Introducing OpenMythos
An open-source, first-principles theoretical reconstruction of Claude Mythos, implemented in PyTorch.
The architecture instantiates a looped transformer with a Mixture-of-Experts (MoE) routing mechanism, enabling iterative depth via weight sharing and conditional computation across experts.
My implementation explores the hypothesis that recursive application of a fixed parameterized block, coupled with sparse expert activation, can yield improved efficiency–performance tradeoffs and emergent multi-step reasoning.
Learn more ⬇️🧵
7/8 Investment takeaway:
Don't just watch VRAM demand. Watch:
• Compute density per token
• Cache efficiency
• Interconnect tech
• Specialized recurrent hardware
The next hardware cycle won't look like the last one.
Such a big deal. Alternatives are @UnslothAI and @axolotl_ai
Curious to see whether they will release medium-size models to compete with Alibaba Qwen3.5 series
Finally, V4 is coming
* Set to release next week ahead of the Two Sessions
* Optimised for Chinese chips led by Huawei and Cambricon
* Multi-modal and early tests results are “impressive”
Exclusive: DeepSeek to release long-awaited AI model
as.ft.com/r/cd6577d9-0633-49…
This is a fantastic playbook for autoscaling inference of multiple LLMs with Ray and vLLM. vLLM by itself can only serve one model per process.
Autoscaling LLM inference with Ray + ROCm rocm.blogs.amd.com/ecosystem…
