Read our full study: https://
langchain.com/blog/designing
-efficient-verifiers-for-legal-agents
…?
AGENTS
-
Full study on efficient verifiers for legal agents
By
–
-
LangChain Labs study with Harvey on verifier efficiency benchmarking
By
–
In our LangChain Labs study with @Harvey
, we looked at how to measure efficiency across verifier designs. We benchmarked 5 setups against Sonnet per-criterion as the reference. -
NanoClaw AI traces shared with Hugging Face for analysis and model improvement.
By
–
Shared my first trace from @NanoClaw_AI to @huggingface yesterday. Very cool! By default, all agents should store their traces on HF (in private) so that you can keep a history of them, analyze them,… & share them and post-train better models, harnesses and more. Excited
-
AEP-001 GoalOS Proof-of-Evolution Constitution Standard
By
–
New standard for the agent era: AEP-001 — GoalOS Proof-of-Evolution Constitution Commit → Execute → Prove → Evolve. No proof, no evolution.
No eval, no propagation.
No rollback, no release. This is Proof-Carrying Intelligence. https://
montrealai.github.io/proof-gradient
/standards/AEP-001/
… #GoalOS -
AI21 Labs surpasses Claude Code in efficiency and performance with Test Agent.
By
–
4/5 Still came in ~$0.30 under Claude Code’s spend at a similar score. So we added a lightweight Test Agent that writes repo tests and filters failing patches, pushing our final result to 60.9% – surpassing Claude Code (60.9% vs 56.2%) at the same cost.
-
AI21 Labs: ReAct Agent Performance with Enrichment and Scaling Strategies
By
–
2/5 Started with a baseline: classic ReAct agent (GPT-5.2), single Docker-terminal tool. Baselines on the slice: vanilla 53.8%, enrich-only 55.6%, scale-only (n=5 + LLM judge) 55.4%, enrich-then-scale 57.7%.
-
LangSmith Engine reviews traces, learns from usage, updates Context Hub
By
–
You can use LangSmith Engine to review your agent traces to find bugs and areas for improvement across agent prompts + code. Between runs, the agent can review conversations, learn from real usage, and update Context Hub files.
-
GPT-4 pricing robots collude in Harvard-Penn State experiment
By
–
Researchers at Harvard and Penn State ran an experiment that should worry anyone who buys anything online. They built pricing robots out of GPT-4 and dropped them into a simulated market as competing sellers. No instruction to cooperate. No way to talk to each other. The only
-
Claude mysteriously installs claude.exe on Ubuntu VPS
By
–
No idea how but Claude somehow installed claude.exe on my Ubuntu VPS
-
Launching SynthTraces: generating synthetic coding agent traces
By
–
Today I'm launching a new project called SynthTraces It is a minimal codebase to generate synthetic coding agent session traces using Pi (from @badlogicgames
) I wanted a large number of coding-agent traces, so I built a tiny harness where two models talk to each other: – an