
Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
A company optimized its browser agent, a tool that automates work by navigating websites and filling out forms, by using an AI model to identify inefficiencies in the agent's workflow. The optimization reduced the estimated model cost by 76 times and made the runs 5 times faster, bringing the average cost down to $0.47 per run. This matters because at scale, small inefficiencies add up significantly, and the improvements allow the company to offer customers faster and more capable models while keeping operating costs sustainable. An engineer directed the AI model to investigate, test improvements, and compare results, work that would have taken one to two months by hand but took about a week with the AI's assistance.

Sakana AI has published Beyond Imitation, a TMLR research paper on LLM-assisted peer review built around error detection. Most AI reviewers are graded on how closely they copy human reviews. This work asks a harder question: can an AI reviewer find a planted mistake? The research team ships two pieces: a Contradiction Benchmark and a Multi-Layered Review (MLR) system. For developers building research agents, the lesson is practical. Both system design and model choice move error detection. T

"Staggering." "Overwhelming." "Unprecedented." "Surreal." "Pure insanity." Those were among the descriptions more than three dozen mathematicians reached for in conversations with The Verge as they tried to make sense of the flood of mathematical results OpenAI abruptly dropped on the field this week. Amid the awe, excitement, and uncertainty over the sheer scale of the deluge was a deep-seated anxiety over what it all means - and what comes next. For all their different react

In this tutorial, we implement RRSI (Regularized Recursive Self-Improvement), a method that lets an LLM agent rewrite its own harness, prompts, tools, memory, control flow, and sub-agents around a frozen model, without the harness overfitting to the tasks it evolves on. The full RRSI loop drafts edits with Claude Opus on Vertex AI and scores them inside Docker benchmarks, which is not something a free notebook can run. The part of RRSI that actually carries the paper’s idea, the rules tha
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven