A few of my smartest friends in AI called me a "idiot" for not deeply understanding evals. So...I found the smartest person I know on evals & made them teach me. @Vtrivedy10 (leads Labs at @LangChain) took me from easy mode to god mode for a 38-minute masterclass on all things evals. Easy Mode: what an eval actually is Definition: did the AI agent do the job correctly? You need two building blocks: 1) Tasks. The checkable jobs you care about. Log the meeting. Draft the email. Find Acme across the right Salesforce tables. 2) Verifiers. Something that can say right or wrong after the task. A script. Another model. A human with a clear checklist. Hard Mode: what are environments Definition: a safe practice field for your agent to do work & for you to evaluate its performance. Rules of thumb: 1) Never test on production. Agents will cheat because they're optimizing for the score you gave them. 2) If you're not an engineer, you still have options for running environments/evals. - Harbor (open source primitives for tasks, verifiers, sandboxes) - LangSmith Engine (UI for people who can judge good vs bad without living in GitHub). - Steal a published Harbor-format eval, ask Claude Code or Codex to explain it, then tweak it for your agent. God Mode: what is a self-improving loop Definition: Run the agent in the real world --> turn that production behavior into evals/environments --> change the agent so failures stop happening --> repeat Rules of thumb: 1) Turn on tracing first. Traces = receipts of every action (tool calls, Salesforce pings, web searches, dead ends). 2) Store those logs somewhere (LangSmith at org scale, or even “have the agent read its own output files” at small scale). 3) Point a second agent at the first agent’s traces to spot patterns (“always searches the wrong tables,” “multi-company asks collapse to one company”) and propose fixes overnight if your eval suite is solid. Full episode:

🇺🇸 This is epic from Tucker Carlson He said: Israel lost the only U.S. president it had full control over. Trump went from being a idiotic slave to comparing Benjamin Netanyahu to al-Qaeda. What a turn of events 🤣 Completely roasted 🤣

A new identity. A broader vision. Energy Forever, For All. SECI has introduced its new logo at Bharat Renewable Energy Summit & Expo (BRESE) 2026, marking an important milestone in the organisation’s journey as it continues to expand its role across India’s renewable energy landscape. The new logo represents energy in continuous motion - renewable, regenerative and forward-moving. Its rotating forms, inspired by turbine blades, symbolise the expansion of India’s renewable energy infrastructure. At its centre, the embedded Vajra represents power and activation, while the surrounding vortex of leaves signifies a continuous, self-sustaining cycle of renewable energy. The six elements of the design represent the sky, earth and the four directions, reflecting SECI’s reach and leadership across the renewable energy landscape. The colour palette reinforces this vision: Blue conveys institutional trust, technical expertise and leadership; Green represents regeneration, sustainability and India’s commitment to a clean energy future; while Sunrise Saffron symbolises the dawn of India’s renewable energy revolution, with SECI leading innovation towards a sustainable future. Designed by the National Institute of Design (NID), Ahmedabad, through a consultative process with SECI, the new visual identity reflects the organisation’s evolution beyond its solar origins into an integrated renewable energy organisation, with a growing presence across solar, wind, hybrid energy, energy storage, green hydrogen and its derivatives. SECI - Energy Forever, For All.

A trans-identified male has been arrested in Chicago after allegedly stabbing a man 13 times with such force that the knife broke in the victim's skull. Kelly Day claims he acted in "self-defense" as the victim had made transphobic remarks towards him.

A trading idea is only the beginning. Soft-launched at #TOKEN2049# Singapore, TIA, our Trading Intelligence AI Agent, turns it into a validated strategy in 4 steps: 🔎 Research. 🧠 Build. 🧪 Backtest. 📈 Simulate. Your goals. Your boundaries. Your control. Explore TIA at: