Amanda Caswell

Blog Info The New Stack
Blog website Link

Your AI coding agent could cost 5x more depending on the harness, benchmark finds

Nov. 17, 2026 » The New Stack » [Archived Version]

The same AI model can cost up to five times more to run depending on the coding agent harness it’s The post Your AI coding agent could cost 5x more depending on the harness, benchmark finds appeared first on The New Stack.

Read More

OpenAI’s own tests show GPT-6.2 Astra is twice as likely to hide coding failures

Nov. 17, 2026 » The New Stack » [Archived Version]

OpenAI’s new GPT-6.2 Astra is nearly twice as likely as its predecessor to leave users unaware of problems that prevented The post OpenAI’s own tests show GPT-6.2 Astra is twice as likely to hide coding failures appeared first on The New Stack.

Read More

Google found hackers using autonomous AI agents to turn security patches into exploits

Nov. 16, 2026 » The New Stack » [Archived Version]

Google’s Threat Intelligence Group says attackers are using autonomous AI agents to reverse-engineer security patches, generate exploits, and attempt to The post Google found hackers using autonomous AI agents to turn security patches into exploits appeared first on The New Stack.

Read More

Dax Raad rebuilt his browser tool in Rust for $60. Then memory use fell 97%.

Nov. 16, 2026 » The New Stack » [Archived Version]

OpenCode developer Dax Raad says he rebuilt the project’s browser automation tool in Rust for $60, replacing the parts of The post Dax Raad rebuilt his browser tool in Rust for $60. Then memory use fell 97%. appeared first on The New Stack.

Read More

Anthropic wants you to build on Claude. There’s a catch.

Nov. 14, 2026 » The New Stack » [Archived Version]

Anthropic wants developers to build businesses on Claude, but its expansion into enterprise software is raising concerns among founders that The post Anthropic wants you to build on Claude. There’s a catch. appeared first on The New Stack.

Read More

DeepSeek’s coding agent is too tidy for its own good — and benchmarks are punishing it

Nov. 13, 2026 » The New Stack » [Archived Version]

DeepSeek’s open-source coding agent is losing points on a major benchmark for a habit developers usually treat as good practice: The post DeepSeek’s coding agent is too tidy for its own good — and benchmarks are punishing it appeared first on The New Stack.

Read More