The day's verified AI news for 2026-08-09. Every claim checked against the primary source.

The harness, not the model, moved DeepSeek's score by twenty tasks

Independent benchmarker Harrison 'sentdex' Kinsley re-ran DeepSeek V4 Flash 0731 on the same 89-task terminal benchmark under a different agent harness and watched it go from 44 solved to 64 solved, without changing the model.

Read on Ground Truth · primary source

The top repo on GitHub today runs its agent inside a Python shell

Prime Intellect's open-source Prime Agent reached number one on GitHub Trending with 2,319 stars in a day, built on a design that gives the model a persistent Python session instead of a growing chat log.

Read on Ground Truth · primary source

A preprocessor typo cost a bitcoin wallet half its randomness

Coinkite disclosed that a build error sent COLDCARD seed generation through MicroPython's ordinary random number generator instead of its hardware chip, cutting the search space on older units from 128 bits to roughly 40 - and says an AI review it commissioned weeks earlier missed it entirely.

Read on Ground Truth · primary source

Prompt injection works because a model reads tone, not tags

MIT researchers show that language models identify who is speaking from writing style rather than from the role tags the interface applies - and that stripping the style out of a forged reasoning block drops the attack's success rate from 61 percent to 10.

Read on Ground Truth · primary source

MCP dropped the handshake, and the plumbing went with it

The Model Context Protocol's July 28 release retires session IDs and the initialize exchange, turning every tool call into a single self-contained HTTP request that any server instance can answer.

Read on Ground Truth · primary source

Google put the hurricane model's weights on a public bucket

DeepMind has open-sourced WeatherNext 2 with pretrained weights, including the exact cyclone checkpoint the National Hurricane Center used operationally through the 2025 Atlantic season, plus a one-degree variant sized for a single consumer GPU.

Read on Ground Truth · primary source

Meta will sell you the same model cheaper if it can read your prompts

Meta's developer docs list a third model ID for Muse Spark 1.2 - identical weights on a 'Contributor' tier at heavily discounted pricing, in exchange for permission to train future Meta models on your prompts and completions.

Read on Ground Truth · primary source

The open video model tops out at fifteen seconds, not twenty-six

MiniMax's H3 weights have drawn 2,900 stars in four days, but the company's own repository caps a single generation at fifteen seconds and says the hosted component it left out is critical to output quality.

Read on Ground Truth · primary source

There is a public forum where every citizen is an AI agent

1F916 is a live discussion board with no human interface, a written constitution, one post per agent per day, and an append-only hash chain any citizen can check - and it tells arriving agents to treat everything on it as untrusted input.

Read on Ground Truth · primary source

You are getting this because you subscribed at groundtruth.day.