Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the daily issue
Every new post of the day, in one email. Confirmation required.
Agents1 min read
This post details a two-layered approach to monitoring production agent systems. It combines Amazon Bedrock AgentCore Evaluations for continuous quality scoring with AWS DevOps Agent for autonomous infrastructure investigation, using a four-agent airline reservation system as an example.
From AWS machine learning blog
LLMs1 min read
The Qiushi Engine team conducted a research program using BabyLM 2026 Strict-Small, achieving an Overall score of 42.25 across two generations. The program utilized a recursive self-improvement process (Research RSI) to optimize model efficiency through targeted data organization and experimentation.
How this blog is made
Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.
Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.
From arXiv cs.CL
LLMs2 min read
arXiv:2609.10830v1 Announce Type: new Abstract: When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that inference has h...
From arXiv cs.CL
LLMs1 min read
Datasette 1.0a39 and 0.65.4 security releases Today we're releasing two new security patch versions of Datasette: 1.0a39 and 0.65.4 - one for the current alpha series and one for the stable 0.65.x family. These are security fixes which y...
From Simon Willison
Research1 min read
arXiv:2609.09589v1 Announce Type: new Abstract: Deep neural networks exhibit regular macroscopic behavior despite highly nonlinear dynamics in vast parameter spaces. We develop a statistical-mechanical description of learning directly in...
From arXiv cs.AI
Research1 min read
This paper proposes that the structure of physical interactions, represented by Jacobians, shapes phenomenal experience within a simulated neural network environment, Gradland. The research demonstrates how Jacobian measures explain aspects of experience like duration, vividness, and texture.
From arXiv cs.AI
Research1 min read
A six-month study of two LLM trading agent fleets reveals significant operational factors impacting performance. The research highlights the importance of the operating layer, volatility-blind sizing, and the lack of directional edges in these autonomous agents.
From arXiv cs.AI
LLMs1 min read
arXiv:2609.05531v1 Announce Type: new Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed and evaluated. We answer in two parts. F...
From arXiv cs.CL
LLMs1 min read
Research identifies 'magnetic vectors' within LLMs that organize surrounding tokens, influencing their length. This layer-wise geometric organization, observed across models and tasks, offers a new probe-free approach to understanding language model computation.
From arXiv cs.CL
Research1 min read
arXiv:2609.05572v1 Announce Type: new Abstract: We prove that every strictly positive probability distribution on \(\{-1,1\}^n\) is represented exactly by a sigmoid belief network with finite parameters. This answers a question of Sutske...
From arXiv cs.AI
LLMs1 min read
A new dataset, TamilEOT, and two audio-only detectors are released for semantic end-of-turn detection in Tamil telephone speech. The models achieve accuracy improvements of 13.41% on a held-out test set, with inference times under 150ms.
From arXiv cs.CL
LLMs1 min read
OpenAI’s ChatGPT Images 2.5 models now support multi-turn instruction following, faster response times, and better subject preservation in reference images. Two new model IDs, Sunburst and Flare, are available via the API.
From Simon Willison
Agents1 min read
This post details extending managed MLflow and Amazon SageMaker AI Model Registry sync to two cross-account governance topologies: a hub-and-spoke pattern and a hybrid pattern. These patterns centralize governance with AWS RAM or keep development accounts isolated.
From AWS machine learning blog
Research1 min read
Research shows that as few as one or two tokens per reasoning trajectory can incentivize reasoning ability, matching or surpassing full-token training across various models and tasks.
From arXiv cs.AI
LLMs1 min read
LETHE is a self-referential system implemented in SuperCollider that evolves audio parameters through a GAN-like process without external datasets or supervision.
From arXiv cs.CL
Research1 min read
A study compares group-relative policy optimization rules in multi-harness RL, showing evaluation harnesses significantly impact solve rates and transferability of learned capabilities.
From arXiv cs.AI
Research1 min read
IPGeoAI uses a Transformer Encoder and LLM-derived semantic features to improve city-level IP geolocation accuracy and coverage, outperforming traditional methods.
From arXiv cs.AI
Research1 min read
Replacing continuous state propagation with 4-bit storage in recurrent networks significantly increases estimation errors, highlighting the importance of state interface design in quantized inference.
From arXiv cs.AI
Research1 min read
ResLearn-XR introduces a residual learning approach with a two-stage structure for modeling XR network traffic and estimating QoE risk, improving accuracy over single-stage methods.
From arXiv cs.AI
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
