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 > pg-99-conf-2026-inference-costs

Chip Huyen explains how to cut inference costs without new hardware

20+ hour, 30+ min ago   (775+ words) Ahead of her return to P99 CONF on October 21–22, Chip Huyen’s advice on cutting AI inference costs gets a fresh look in the age of agents....

The New Stack
thenewstack.io > ai-agent-trace-debugging

It passed CI. It passed your evals. The customer still got the wrong answer.

21+ hour, 30+ min ago   (771+ words) Your AI agent returned a 200, passed its faithfulness check, and still answered the wrong question. The evidence that explains why lives in the trace....

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

The AI-native SDLC won't be one process

1+ day, 21+ 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 > aws-pizza-bot-agent-inbox

AWS open-sources Pizza Bot: email-style inbox for background AI agents

3+ day, 12+ hour ago   (280+ words) Two thousand people inside Amazon used early versions - before Pizza Bot was rebuilt as a standalone community project....

The New Stack
thenewstack.io > salesforce-enterprise-ai-harness

"Six tools, one harness": Salesforce loops together a six-pack of favorites

3+ day, 15+ hour ago   (78+ words) Salesforce unveils its Enterprise AI Harness, unifying six platform tools to fix data and workflow gaps between siloed AI agents. (129 chars)...

The New Stack
thenewstack.io > red-hat-ai-multitenancy

Red Hat AI 3.5 tackles the GPU queue that can stall AI pilots

3+ day, 18+ hour ago   (508+ words) Red Hat AI 3.5 brings priority-aware GPU scheduling and tenant isolation to shared infrastructure, plus pre-deployment safety evals via EvalHub....

The New Stack
thenewstack.io > ai-engineering-roles-emerging

47,000 job listings reveal the engineering roles that AI is creating

3+ day, 22+ hour ago   (952+ words) Every major transformation in tech has led to roles merging, then new ones emerging. Friction between developers and operations drove the creation of the DevOps engineer. Then, when security needed to be considered throughout the delivery pipeline, DevSecOps emerged. The…...

The New Stack
thenewstack.io > stop-ai-code-sprawl

Stop AI code sprawl before it destroys your software design

3+ day, 23+ hour ago   (450+ words) Prevent AI code sprawl and Comprehension Debt. Use Python tools like pytest-archon to enforce Executable Architecture in your CI/CD....

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, 15+ 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, 27+ min 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…...