Gold, oil and gas in 15-minute rounds
That's less forecasting, more reflexes. Prediction markets are turning into a trading screen, and the shorter the window, the more it's speed over opinion
Would you take a 15-minute window, or stick to the big questions?
Commodities, up or down?
Gold, silver, oil, & natural gas up/downs are now live on Polymarket.
15 minute, hourly, & daily.
3
15
423
1 AI agent: up to 4x faster code. 32 agents together: 19x. (Replit's own test, 13 tasks.)
Replit Missions: you set the goal, the budget and what needs your OK. A swarm does the work, an AI judge checks it
Would you hand a swarm $1,000 and a goal?
2
8
288
Sources: Replit blog replit.com/blog/introducing-… · Amjad's post xitter.gq/amasad/status/21227544…
LLMs have gotten more autonomous recently but when you give them a goal they often misunderstand you, work aimlessly, and waste your tokens.
Today, we’re introducing Missions—the world’s first agentic swarm harness that can accomplish any goal you give them within set budget.
Try it today with something like “get me my first 10 customers:” replit.com/blog/introducing-…
20
OpenAI says GPT-6.2 Astra beats Claude Fable 5.2 by 5.5 points at "just 5% of the cost."
The footnote: Fable's results exclude nine tasks that used a fallback model
First outside test (Every): writing is a step back, coding stops early
Big claim. Wait for the verdict
5
117
Polymarket International cuts taker fees from Friday, Nov 20
Coefficient → 0.01 for politics (excl. elections), culture, weather, economics, mentions and most crypto
Biggest drop: crypto outside BTC 5/15m, 0.07 → 0.01. Sports stays
Lower fees don’t make a bad trade good
Lower fees are coming to more markets on Polymarket International.
Starting Friday, Nov 20 at 11:59 PM UTC, we’re dropping the taker fee coefficient to 0.01 across politics, culture, weather, economics, mentions, & non-5/15m-BTC crypto on polymarket.com.
Full breakdown 🧵
polymarket.com/r/7OeW4Jd
6
20
432
The real skill with open models isn't running them. It's routing
Small model answers first and says how sure it is. Only unsure tasks go to the frontier model. A test, not the model, decides if it's done
Cheap by default. Expensive by exception
Flight cancelled. 187 people ahead of you in line
You stay in your seat. Your AI phones the airline, waits on hold, rebooks you
That's the viral claim. The calling feature is real: Grok Bot can dial for you now
The flight? Never named
Would you trust it with your trip?
4
16
482
Viral post:
Grok's announcement: xitter.gq/grok/status/2118138308…
holy f*ck... Elon Musk's team just made airport rebooking lines useless
my flight got cancelled and 187 people were ahead of me at the desk. my Grok Bot rebooked me before the line moved 17 people
Grok Bot makes phone calls now. it sits on hold, talks to the agent and says up front it's an AI
what it did while I stood in line:
→ sat through 11 minutes of hold music
→ got me on the 7:40 AM flight tomorrow
→ the airline cancelled, so it asked for a hotel and meals. got both
→ "aisle seat is $49 extra" it didn't pay. it asked me. I took the free middle seat
→ texted my wife the new landing time (signed Grok Bot) and set my alarm
14 minutes on the phone. I walked out of the line, 168 people still in it
all it took was 3 rules I sent it once:
1. on every call, say you're an AI calling for me
2. ask for everything I'm owed, nothing made up
3. anything that costs money: ask me first
the Grok Bot Research Desk setup is in my article. read it below ↓
Readers added context they thought people might want to know
This post presents a staged demo video of a hypothetical Grok Bot rebooking scenario on the fictional airline Bluepeak Air as a real personal event.
x.com/gdalt3/status/…
en.wikipedia.org/wiki/List_of_a…
teslanorth.com/2026/11/04/gro…
x.com/bot/status/211…
29
~12,000 flights cancelled. 3,500 planes in the air. A nationwide ground stop
Hack? AI? The FAA’s early answer: a data flood, 1,000 connection attempts every 4–5 seconds, from a site getting a new router
Polymarket: hack 3%, AI 2%
Boring cause. Huge chaos
4
21
366
Market: polymarket.com/event/what-te…
2
30
This text-to-speech model has never heard a real human voice
It learned from 19 hours of speech made by a bigger AI. Result: 4.5M parameters, 18 MB, ~70x real time on a CPU
Total cost: $9.56. Weights are open
Send this to anyone who thinks AI needs a data center
I trained a text-to-speech model that has never heard a real human voice.
4.5M parameters. 18 MB. Runs on a CPU.
Meet tiny-voca
8
21
650
Source: author's thread
Code & docs: github.com/n4ze3m/tiny-voca
I trained a text-to-speech model that has never heard a real human voice.
4.5M parameters. 18 MB. Runs on a CPU.
Meet tiny-voca
1
2
59
Your AI agent says “it works.” Now it has to show the video
Expo launched cloud simulators for agents: the agent runs your app on a cloud iPhone, taps through its own change, and brings back a screen recording as proof
No Mac needed
Merge a PR with video, not “trust me”?
1
15
473











