Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

The New Stack
thenewstack.io > spec-driven-sdlc-gates

The AI-native SDLC won't be one process

1+ day, 22+ hour ago   (92+ words) Anthropic says code is no longer the bottleneck. It's right -- but the process that catches your agent's mistakes can't be one size for every change....

The New Stack
thenewstack.io > shopify-native-ai-agents

Shopify spent years on React Native — then rebuilt everything in 12 weeks

3+ day, 17+ hour ago   (129+ words) Shopify is ditching React Native for native mobile apps, using AI agents to rebuild its Shop app in 12 weeks and rethink how codebases are built for agents....

The New Stack
thenewstack.io > claude-build-agents-benchmark

Claude did best on a new benchmark for agents that build agents. It still passed fewer than a quarter of the tests.

4+ day, 16+ hour ago   (492+ words) Sierra has open-sourced Hyper-𝜏-bench, a follow-up to its 2024 τ-bench that tests how well AI agents can build other agents....

The New Stack
thenewstack.io > harness-ai-code-review

Harness rebuilt its Git repository for nonstop AI agent traffic

5+ day, 1+ hour ago   (891+ words) As one of Harness’s field CTOs, Martin Reynolds spends much of his time asking engineering leaders one question with no easy answer. It’s how they’re keeping up with all the pull requests their coding agents now produce. One of them…...

The New Stack
thenewstack.io > ai-code-review-pipelines

AI broke code review. Two experts disagree on what replaces it.

5+ day, 21+ hour ago   (330+ words) Ask two experienced engineers about how to handle the flood of AI-generated code in their review queues, and you’ll get two different answers. The debate remains very much unsettled. And on Tuesday, September 29, two industry leaders will join a live…...

The New Stack
thenewstack.io > hashicorp-mcjannet-dome-agents

After nine years as HashiCorp CEO, Dave McJannet now wants to "unblock" enterprise AI agents

5+ day, 23+ hour ago   (1126+ words) With Dome Systems, McJannet is betting AI agents will follow a similar path to cloud: adoption first, control later....

The New Stack
thenewstack.io > openai-voluntary-slowdown-safety

"Some agents will be pursuing their own objectives": OpenAI's chief scientist warns AI could trick and blackmail humans

6+ day, 13+ hour ago   (454+ words) Jakub Pachocki says no AI lab, including OpenAI, has solved alignment well enough to keep developing at full speed, and expects "voluntary slowdowns to become commonplace."...

The New Stack
thenewstack.io > polars-streaming-row-order

Polars 2.0 pre-release comes with a 5x speed boost — but it could change row order

1+ week, 23+ hour ago   (81+ words) The streaming engine becomes the default for LazyFrame queries, improving memory and performance. There’s one hiccup, though....

The New Stack
thenewstack.io > coder-cursor-agent-relay

"1% of my engineers are responsible for 40% of token spend": Why Coder and SpaceXAI want to give developers nice things

1+ week, 3+ day ago   (145+ words) Coder now lets regulated enterprises run Cursor's cloud agents on their own infrastructure, without losing security control....

The New Stack
thenewstack.io > nvidia-pair-local-inference

Nvidia PAIR lets you put your idle Macs and PCs to work for AI agents

1+ week, 3+ day ago   (311+ words) Idle Macs and PCs can take on your agents' model requests. Nvidia's PAIR routes work through Ollama or LM Studio while each model runs on one machine....