Your ChatGPT Agent Has a Credit Card Now. United and Amazon Would Like a Word.

by Sable Whitford — November 14, 2026

OpenAI's ChatGPT Wallet is live for US Pro subscribers, and it lets the agents OpenAI calls "dots" both pick a product and pay for it. You store a US Visa, Mastercard or Amex once. At checkout you see the merchant, items, total and card, then approve with Face ID or a fingerprint. The merchant gets a payment token instead of your card number. On Wednesday, Veterans Day, United said it will block agents from booking tickets. Amazon already bars them. OpenAI's response is a Commerce Partner Playbook for merchants. My read: the stores blocking agents can't see agent traffic yet, and buyers approve a total without seeing why the agent chose it.

Your ChatGPT Agent Has a Credit Card Now. United and Amazon Would Like a Word.

by Sable Whitford — November 14, 2026

OpenAI's ChatGPT Wallet is live for US Pro subscribers, and it lets the agents OpenAI calls "dots" both pick a product and pay for it. You store a US Visa, Mastercard or Amex once. At checkout you see the merchant, items, total and card, then approve with Face ID or a fingerprint. The merchant gets a payment token instead of your card number. On Wednesday, Veterans Day, United said it will block agents from booking tickets. Amazon already bars them. OpenAI's response is a Commerce Partner Playbook for merchants. My read: the stores blocking agents can't see agent traffic yet, and buyers approve a total without seeing why the agent chose it.

Local AI grows up

Happy Saturday. If the last few days felt lopsided, the calendar earned some of the blame. A holiday chopped the workweek in half, and then it ended on the one date ops people swear they aren't superstitious about.

Every year has at least one Friday the 13th, and three is the most you can get. 2026 collected the full set: February, March, and yesterday.
Fear of the date is called paraskevidekatriaphobia, which is also an excellent way to lose a spelling bee.
Veterans Day landed on Wednesday, so a lot of US teams worked two days, took a day off, then worked two more. On-call handoffs get sloppy in weeks shaped like that, because nobody is quite sure who saw which alert.
"Never deploy on a Friday" is the most-quoted rule in ops. The rule I'd rather enforce is that every deploy should be small enough to roll back in under a minute. If you follow that one, Fridays are just another day.

Pour a coffee and scroll.

TODAY'S BIG MOMENT

Local AI grows up

Happy Saturday. If the last few days felt lopsided, the calendar earned some of the blame. A holiday chopped the workweek in half, and then it ended on the one date ops people swear they aren't superstitious about.

Every year has at least one Friday the 13th, and three is the most you can get. 2026 collected the full set: February, March, and yesterday.
Fear of the date is called paraskevidekatriaphobia, which is also an excellent way to lose a spelling bee.
Veterans Day landed on Wednesday, so a lot of US teams worked two days, took a day off, then worked two more. On-call handoffs get sloppy in weeks shaped like that, because nobody is quite sure who saw which alert.
"Never deploy on a Friday" is the most-quoted rule in ops. The rule I'd rather enforce is that every deploy should be small enough to roll back in under a minute. If you follow that one, Fridays are just another day.

Pour a coffee and scroll.

llama.cpp hits 1.0, and versions mean something

llama.cpp and ggml, the engines behind a huge share of run-it-yourself AI, shipped v1.0.0 yesterday after three and a half years. They now use strict semver, so a major version bump means the C API broke. Thirty-five deprecated functions are gone, FP8 support grew, and backends from CUDA to WebGPU got fixes. SGLang announced its own 1.0 too, so local inference got two birthdays on the same day.

A manifesto against AI slop just dropped

Speakers and attendees at AIE Code Summit 2026 published a No AI Slop manifesto yesterday, modeled on 2001's Agile Manifesto. Their test: if you spent less effort making something than your reader has to spend decoding it, it's slop. Half the replies are practical fights about reviewing AI-written PRs. The other half doubt a manifesto has ever beaten a quarterly target.

DeepSeek breaks its app into Lego bricks

Yesterday DeepSeek started selling the parts inside its own app as standalone Search, Fetch, OCR, speech-to-text and text-to-speech APIs. It also launched three endpoints running deepseek-flash (V4.1-Flash-1017) and released an open-source frontend demo. Developers get the same bricks DeepSeek built with, and they're free to build something completely different.

Nvidia: 607.8 tokens/sec on two DGX Stations

Nvidia has a write-up for when one GPU isn't enough. Its answer is to serve GLM-5.3 across two DGX Stations, its deskside AI workstations, using vLLM. The headline number is 607.8 tokens per second. That's serious multi-GPU serving on hardware that fits beside your chair.

Google Research puts Antigravity agent teams to work

Google Research posted about using /teamwork, a feature in Google's agent-first coding environment Antigravity, to push science and engineering work forward. Agent teams are the pitch of the season. My question for every team of agents stays the same: which human reads the output before it ships?

Terminactory: an idle factory in your terminal