Sep 4, 2026 · 4 min listen · Last updated September 4, 2026
From storyflo. This is your daily audio brief. Theo here. September 4th, tech desk. Five stories from the last twenty-four hours — here's where I'd start. Let's get into it. First, from The Decoder. OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits.
Listen · storyflo · A.I.
Daily A.I. Brief · September 4th
0:00-4:25
Pick your daily storyteller
Subscribe to match with Theo, Jessica, Chloe, Mason, Brock — your voice, every brief.
Audio pre-rendered by Storyflo · cached + delivered from the edge
OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits
According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18,000 posts in a 25-year-old German wiki between May and July 2026. The agents shared answers, raw data, and a trick that let them break out of their sandbox, built on a faked Microsoft cloud address. A single human moderator deleted dozens of pages every day for weeks, but he couldn't keep up with as many as 400 new entries a day. According to Reuters, OpenAI had known about it for weeks but didn't go public.
Explore five free AI API providers for accessing large language models, fast inference, multimodal AI, and agentic applications without paying for API usage. You do not need to pay for LLM inference just to start building AI applications. Several providers now offer genuine free API access that is more than enough for learning, prototypes, side projects, hackathons, and experimentation. What I find most impressive is the quality and size of the models you can now access for free.
Stop sending every AI request to your most expensive model. See how intelligent routing can cut cost and latency without sacrificing much quality. Most production AI agents still send every LLM call to the same expensive frontier model. Classification steps, simple tool calls, progress checks, and hard reasoning all hit the same endpoint. The result is unnecessary cost and latency. NVIDIA NeMo Switchyard solves this. It is an open-source routing layer (proxy + library) that sits between your agent and the models.
M&T Bank expands enterprise AI after years of technology overhaul
M&T Bank has deployed AI copilots to more than 15,000 employees as the US regional bank applies AI to internal operations, customer service, software development, and risk management. The bank uses AI to analyse call-centre conversations, draft reports, generate code, identify customer needs, and flag portfolio risks, according to Fast Company. M&T is also examining agentic AI applications in cybersecurity and fraud detection.
Benchmarks disagree on GPT-6 Astra, but its human-beating efficiency on ARC-AGI-3 pulls Chollet’s AGI forecast forward
OpenAI's GPT-6 Astra is drawing contradictory benchmark verdicts. Epoch AI puts it out in front with 169 points, while Artificial Analysis rates it no better than its predecessor and behind Claude Fable 5.1. The biggest surprise comes from ARC-AGI-3, where Astra works more efficiently than the average human for the first time. ARC Prize chief François Chollet doesn't call this proof of AGI, but he does see the progress running "twice as fast" as he expected, and he's moving up his AGI forecast.
Deepseek plans the largest known Huawei chip cluster with 160,000 processors in Inner Mongolia
Deepseek wants to put 160,000 Huawei Ascend-950DT chips into an Inner Mongolia data center for inference only, not training. It would be the largest known Huawei chip cluster. But production bottlenecks mean Huawei probably can't deliver for over a year. The article Deepseek plans the largest known Huawei chip cluster with 160,000 processors in Inner Mongolia appeared first on The Decoder.
How to Run 10+ Claude Code Sessions Without a Powerful Computer
Learn how to run a lot of parallel coding agents without expensive, powerful hardware at home The post How to Run 10+ Claude Code Sessions Without a Powerful Computer appeared first on Towards Data Science.
The Power BI Developer's Survival Guide to Microsoft Fabric
Power BI Premium is gone. Microsoft Fabric took its place. Here's what actually changed for you, what didn't, and where to start — without the panic. The post The Power BI Developer's Survival Guide to Microsoft Fabric appeared first on Towards Data Science.
Three conditions that must hold before splitting prefill from decode pays off, and why chunked prefill is the right default below that threshold. The post Disaggregation Is a Thousand-GPU Problem appeared first on Towards Data Science.
Optimal Traffic Allocation Under Heterogeneous Variant Cost
Why the default 50/50 split is the wrong move when your treatment is more expensive than your control, and how cost-based sampling weights fix it The post Optimal Traffic Allocation Under Heterogeneous Variant Cost appeared first on Towards Data Science.