i'm just an advisor, cant take credit. team is doing great with devin 3.0 and devin desktop
LLMS
-
Hardware limitations on sparse neural activation in LLMs
By
–
The human brain is incredibly efficient because it only activates the specific neurons needed for a thought. Modern LLMs naturally try to do this too (> 95% of neurons in feedforward layers stay silent for any given word), but our hardware punishes them for it. One of the most
-
Using AI Models to Optimize Prompt Routing and API Budget
By
–
using a 1T parameter model to parse a 3-line JSON is a crime 😅@OrcaRouter just dropped.
— Charly Wargnier (@DataChaz) 8 mai 2026
It automatically routes prompts based on complexity to protect your API budget 👀
CFOs after reading this: https://t.co/bSrxIcukLZ pic.twitter.com/5YG9swOHUCusing a 1T parameter model to parse a 3-line JSON is a crime @OrcaRouter just dropped. It automatically routes prompts based on complexity to protect your API budget CFOs after reading this:
-
Optimiser les LLM avec la sparsité adaptée au GPU
By
–
How do we make LLMs faster and lighter? Don’t force the GPU to adapt to sparsity. Reshape the sparsity to fit the GPU! ⚡️
— Sakana AI (@SakanaAILabs) 8 mai 2026
Excited to share our new #ICML2026 paper in collaboration with @NVIDIA: "Sparser, Faster, Lighter Transformer Language Models". This work introduces new… pic.twitter.com/ehByWHIh6IHow do we make LLMs faster and lighter? Don’t force the GPU to adapt to sparsity. Reshape the sparsity to fit the GPU! Excited to share our new #ICML2026 paper in collaboration with @NVIDIA
: "Sparser, Faster, Lighter Transformer Language Models". This work introduces new -
Internal Manual for Building AI Agent Skills Published
By
–
We've published our internal manual for building agent skills. Skills require a new way of thinking for developers.
-
Addressing High Costs in AI Coding via Open-Source Models
By
–
ai coding is getting expensive use more open models!
-
SkillOS: Skill Curation for Self-Evolving Agents
By
–
SkillOS Learning Skill Curation for Self-Evolving Agents paper: https://
huggingface.co/papers/2605.06
614
… -
Apple introduces TIDE: Every Layer Knows the Token Beneath the Context
By
–
Apple presents TIDE Every Layer Knows the Token Beneath the Context paper: https://
huggingface.co/papers/2605.06
216
… -
LLMs’ Math Progress Accelerates Rapidly
By
–
It's surprising to see the pace of progress of LLMs (which until not long ago were very bad at math) achieving ever greater milestones. Take a look at the graph above. The progress curve is getting faster and faster. I'll leave the link to the paper here: https://
arxiv.org/abs/2605.06651