Oh, and in case that's interesting: one data point supporting the value of diversity in point of view from our work on ReviewerToo is that we get the best results when we pool more simulated reviewing personas in our system
AGENTS
-
Open-Source Agent Framework Automatically Fixes Its Own Production Bugs
By
–
Someone built an agent that fixes its own bugs on autopilot. Agents fail in production constantly. Hallucinated tool calls, refusal loops, redundant arguments. Fixing these usually means engineers digging through thousands of traces by hand. A new open-source framework
-
Codex App Ships GPT-5.5 Browser Control Sheets Slides and More
By
–
Codex for everything. Over the last 2 weeks, we shipped a pretty big set of updates: GPT-5.5, browser control, Sheets & Slides, Docs & PDFs, OS-wide dictation, auto-review mode, /pets, and a .tex plugin. The whole app also got better: dynamic UI for the task at hand, ~20%
-
Frontier Agent Benchmarking Struggles to Capture Real Progress
By
–
Its getting hard to benchmark frontier agent performance on longer tasks. Repeated measurement is very expensive and there are differences between using models in harnesses versus via APIs. I suspect benchmarks understate progress, they are built for models, not harnessed agents
-
New AI Research Age Emerges Beyond Scale Alone
By
–
In the last decade, I championed scale and engineering. Scale continues to be essential but it’s now time to innovate beyond scale alone. We are entering a new research age. Thanks to more compute, open-source, code and math assistants, any research team (or LLM agent) can now
-
Developer Holds Back AI Agents From Getting X Account
By
–
My agents want an X account. I am holding back. 🙂
-
Skeptic Calls AI Agents Hype ‘Certifiable Bullshit’
By
–
I think all this agents stuff is still certifiable bullshit
-
Two Types of Engineers for Building Great AI Agents
By
–
Securing the top spot at the BuildAI Pitch Event! SarthhakAI, led by Satvik Kalra and Trapti Kalra, wins ₹2,00,000 for its impactful AI-driven solution addressing real-world challenges. #BuildAI #IndiaAI #AIPitch #AIStartups #Innovation @kavitabha @GoI_MeitY @_DigitalIndia
-
Run Codex Inside OpenClaw With Plugin Harness
By
–
Run codex inside OpenClaw! https://
docs.openclaw.ai/plugins/codex-
harness
… -
Codex Ships GPT-5.5 Browser Control Sheets Docs and More
By
–
Codex for everything. Over the last 2 weeks, we shipped a pretty big set of updates: GPT-5.5, browser control, Sheets & Slides, Docs & PDFs, OS-wide dictation, auto-review mode, /pets, and a .tex plugin. The whole app also got better: dynamic UI for the task at hand, ~20%