Weak verifier, weak improvement. If you measure “cleaner writing,” the agent may learn to sound polished. If you measure “more engagement,” it may learn clickbait. If you measure “passes tests,” it may learn to satisfy the test suite without solving the real problem. The
INNOVATION
-
AI Generation Quality Assessment Beyond Candidate Quantity
By
–
Generating candidates is now easy compared to back then. An AI can generate: 100 prompt variants 50 code changes 20 tool-routing ideas 10 eval rewrites 5 new workflows
The question is not “can it come up with changes?”
The question is “which changes are actually better?” -
Verifiers: The Key to Evaluating AI Model Performance
By
–
That is where the verifier comes in. A verifier is whatever checks the work. It can be: test results human review a simulator a benchmark real user outcomes a second model judging the first model
The verifier is the thing that decides what gets kept. -
Karpathy’s AutoResearch: 700 Experiments, 20 Key Optimizations Found
By
–
Karpathy’s AutoResearch made this concrete. One markdown prompt. 630 lines of training code. One GPU. 2 days.
It ran 700 experiments and found 20 training optimizations.
Most people was impressed by on the 700 experiments.
But what most people missed out is what decided which 20 -
The Verification Problem in AI Self-Improvement Systems
By
–
AI agents can now generate endless ways to improve themselves. New prompts. New code. New plans. New experiments. New tool calls.
That is not the bottleneck anymore.
The bottleneck is the verifier.
How do you know the new version is actually better? -
Self-Improvement Loops: How AI Systems Learn Through Feedback
By
–
First, what’s actually happening. A self-improvement loop is simple: try a change test the change keep what helped throw away what did not repeat
That’s it.
The system is not magically becoming intelligent.
It is running a feedback loop. -
SAS Innovate Event Brings Fun and Record-Breaking Achievement
By
–
Thanks for bringing the fun (and the record!) to #SASInnovate
-
Building and Deploying Agents with DeepAgents Deploy
By
–
That's a quick tour through building and deploying a simple agent with DeepAgents deploy Was just a markdown file, a json file, and toml file Easy to set up, but robust deployment by the end Try out deepagents deploy! Full docs here:
-
Agent Deployment via MCP, A2A and Remote Graph API
By
–
As part of this deployment, you can interact with the agent in several ways We expose the agent via MCP and A2A, as well as with as a "remote graph" API, which means you can interact with as you would a normal in-memory graph See streaming docs here: https://
docs.langchain.com/langsmith/stre
aming
… -
Deployment Guide: Baseten and LangSmith Setup Steps
By
–
Final steps before deploying: 1/ Delete the skills folder the scaffolding created (not needed for now) 2/ Add environment variables. Need a Baseten API key (for the model) as well as a LangSmith API key for deployment LangSmith: https://
smith.langchain.com