@ColtonP99962103@h00mankind@wunderkuh@superdoteng https://t.co/jttNvQQXE4
"Starting June 15, 2026, Claude Agent SDK and claude -p usage no longer counts toward your Claude plan’s usage limits."
I have zero emails from Anthropic countering this.
I’m sure you can figure out a way to “test” this and test it tomorrow to verify.
ex. Jane Street quant built a Polymarket bot with a 99.3% win rate and turned $1.2K → $865K in 6 months
I analyzed his 29K trades with Opus 4.7 → reverse-engineered strategy based on 72M trades dataset
rented VPS + connected Hermes agent + Binance API
result 363% ROI in 3 days
run your agent in 5 simple steps:
• rent a VPS on Hetzner - $6.00
• install Hermes CLI using one-liner code - free
• plug Opus 4.7 + TG bot + Polymarket API
• run paper trading on 72M trades (John Backer) dataset
• sent Hermes step-by-step prompts from article
apply Kelly Criterion sizing & give agent at least $100 to run {50-100} trades for self-learning
bot profile: https://t.co/JgYrLNoos3
start copy-trading in 2 clicks using Ares: https://t.co/A7GBN2Eok2
self-learning agents combined with quant models are the best setup for Polymarket crypto trading.
@maga0idf@vivekgirotra@jackclarkSF What is contained in dark information? User desired by agents exclusively for agents (encrypted)? Does this term dark information have a strict meaning?
What does your reply really mean?
@_LaurentB@LinusEkenstam Way to bet on the least possible thing to happen. Also it would be awful given how censoring the company is value system wise.
@vladfaust@fofrAI@Must_be_Ash And or even a note from a single model provider that the models do anything unique with json or yaml or whatever structure people seem to be promoting use of…
@vladfaust@fofrAI@Must_be_Ash I don’t ever see any concrete info that json leads to higher quality. I’ve asked every time I see it brought up. If anything it consumes context - which is bad. If people like it as a “workflow” aid I guess. But “better” quality. I’m still waiting for evidence…
@ChaceMcLees@chrisgpt@emanuelturis@Casey The AI slop being addictive is completely different point than the sidewalk metaphor and stopping though… those are diff topics altogether.