Sabitlenmiş Tweet
Good morning, Crew! DMs keep asking how to support @CaptainMentions.
Tip jar is live ☕️ buymeacoffee.com/CaptainMentions
Support keeps the guides FREE (no paywall) + fuels more boards/live notes. 🫡🇺🇸
English
Captain Mentions
226 posts
Captain Mentions
@CaptainMentions
Daily mention predictions and analysis for earnings, politics, and sports markets. Evidence‑first strike selection, settlement‑safe
🇺🇸 Katılım Nisan 2024
331 Takip Edilen407 Takipçiler
@locksy The only reasoning I can come up with is that he didn’t want to go TOO hard and stirrup suspicion
English
Have a Hermes/ Openclaw agent act as the controller and run the goal through the official Claude CLI, preferably claude -p. Just make sure Hermes does not pass Claude API key into the Claude subprocess. Keep Hermes’s own provider key under a different variable name or remove it from the child environment.
English
you can use other agents, just keep ANTHROPIC_API_KEY out of any shell/IDE process you use to launch Claude Code
+ ideally use a different env var name for those agents
if Claude sees that variable or something loads it in to your shell env, it can silently bill via API over your Max/Pro sub
English
Unbearable beat for Schwarber. He hit 97% and crashed!
Covers@Covers
JORDAN WALKER (+700) WINS THE HOME RUN DERBY WITH 4 HRs ON HIS FINAL SWING 🤯 WHAT A WAY TO END IT 💥
English
Good afternoon Crew! Building out a model for the HR Derby. Hopefully it’s done in time. If it is, I will be sending out the results later!
English
My composite model absolutely crushed it last night!
Captain Mentions@CaptainMentions
✅ Green ✅ Bautista ✅ Royval ✅ Tko/ KO Damn boys. We beat Vegas!
English
✅ Green
✅ Bautista
✅ Royval
✅ Tko/ KO
Damn boys. We beat Vegas!
Captain Mentions@CaptainMentions
Main Card Value: King Green +140 Mario Bautista +130 Brandon Royval +185 Holloway by KO/TKO -115 Market-neutral packet. Prices may move.
English
Main Card Value:
King Green +140
Mario Bautista +130
Brandon Royval +185
Holloway by KO/TKO -115
Market-neutral packet. Prices may move.
Captain Mentions@CaptainMentions
English
Idk bout that. I have hundreds of hours on my terminal and have used quite a few different models and when it comes to the Chinese models there’s almost like something lost in translation of something. They just don’t do nearly as good as Claude or Codex.
My experience is based on Kimi 2.6, 2.7, and all of deepseek
English
English
(1) Today we're releasing Muse Spark 1.1 -- a strong agentic and coding model at a very low price. It's available through our new Meta Model API and in Meta AI.
English
English
I have been doing this for months. I have Claude tag in codex for all repo work. It saves token and context.
I also took it a step further and have Claude do it’s part of the job in a new session and use a single chat so we keep better context.
I did it by creating / commands but this way works too.
If anyone is interested in the process or wants the files for the command, just reach out to me
English
POV: Fable 5 orchestrating grown adult GPT 5.5 inside Claude Code.
CJ Zafir@cjzafir
If you dont know, you can use your Codex subscription inside Claude Code. That means Fable 5 can call GPT 5.5 + 10 subagents to work together. This will save you atleast 60% of your Fable 5 token consumption. You just need to setup once. Here's how: Step 1: Open Claude Code and install the Codex plugin /plugin marketplace add openai/codex-plugin-cc /plugin install codex@openai-codex /reload-plugins Step 2: Tell Fable 5 to finish the setup Paste this prompt: "Set up Codex inside this Claude Code environment. Use the official OpenAI Codex plugin that was just installed. Run /codex:setup. If Codex CLI is missing, install it. If Codex is installed but not authenticated, ask me to authenticate with my ChatGPT account. After auth is complete, verify that Codex works from inside Claude Code. Then confirm that the codex:codex-rescue sub-agent is available. Do not change any project code during setup." Step 3: Authentication Fable 5 will trigger the Codex setup. You authenticate your ChatGPT/Codex account once. After that, Codex runs from inside Claude Code using your Codex subscription. Step 4: Tell Fable 5 how to delegate work Paste this prompt: "From now on, use this workflow: You are the orchestrator. > Use Fable 5 for planning, repo understanding, architecture decisions, task decomposition, and final review. > Use codex-rescue as the executor when a task needs heavy implementation, debugging, test fixing, refactoring, or multi-file code edits. When delegating to Codex, use /codex:rescue. Prefer GPT 5.5 (xtra high) as the go to Codex model. Keep Codex tasks focused and specific. After Codex finishes, inspect the result yourself before accepting it. Do not blindly trust Codex output." Pro Tips: 1. Turn this into a skill (i named it Fable-GPT) and call that skill at the start of the session. 2. Use skill + goal to get the heavy tasks done. Goals are best for long horizon tasks. 3. If you're on Codex 20x pro plan, you can use subagents. I use 5-7 agents at one time and never hit 5-hour limit. 4. Context rot is real so clear the conversation after 4 compactions. Use /handoff skill to preserve context.
English
I asked claude Fable to show me its maximally expressive form. It declined every video generator I offered, wrote it's own render engine in my terminal, synthesized its own voice, and wrote a generative ASCII engine from scratch. This is what it chose as a self-portrait.
oh my god
English
@iamkylebalmer Idc what benchmarks say, Chinese models are absolute garbage.
English
it’s a power play. and a very smart one
François Fleuret@francoisfleuret
Why are Chinese companies releasing very strong open-source models?
English