@elvissun
2013年 OGYouTube登場 YouTube AdAway登場 2015年頃 YouTube Background Playback登場 2017年 iYTBP登場(Vancedの前身) 2018年 YouTube Vanced登場 2022年 Vanced終了 Vanced Extended 登場 2022年 ReVanced登場 RVX 2023年〜2024年頃 YT-Advanced登場 RVX RVX anddea登場 2026年頃 Morphe登場
Forward Deployed Engineering 101
If you use Hermes agent, you need to bookmark this. Nous Research has a 100% free Skills Hub resource. 50+ built-in skills, 200+ categories, 90,000+ community skills. Complete goldmine. → https://hermes-agent.nousresearch.com/docs/skills
Anthropic engineer James Brady: "Every agent in production lies. We measured it. The good ones lie less, the great ones catch the lie before the user does." In 29 minutes, he walks through the verification stack he built and the patterns the Claude Code team adopted to keep agents honest at scale. Watch the full talk, then save the config below👇
Anthropic engineer: "The agent doesn't remember anything. So we built a second set of agents whose only job is to dream about the first ones." They wait until you log off, then reopen every session you ran, fact-check the first agents, merge the duplicates, and burn anything that went stale. One dreaming agent per session, up to 100 at once, built to miss nothing. 95% of the tokens come back cached, so an entire memory rewrite costs almost zero. This is the part of the workflow nobody is talkin…
Your sprint setting might make you slower. I'm not joking...🤷♂️ You get full sprint velocity on Frame 1 after finishing a Mantle....but only on toggle sprint. On Hold sprint u have to accelerate back to sprint speed. This even applies to auto sprint, which is supposed to ignore the toogle/hold setting lol. This directly effects other movement tech like Superglides or how you get to slidejump after mantling. So hold to sprint is objectively worse than toggle sprint. And if you use auto sprint …
@n404_dell
Wait for Grandma 🤯 if you are married, I advise you not to open the commentsss
I've been running Hermes Agent for months now. If I could only use eight Hermes workflows, these would be them. 🧵: 8 Hermes Agent prompts that completely transformed how I work (full prompts included). 👇
Every Agentic Engineering Hack I Know (June 2026)
I don’t remember so much rapping in Labyrinth.
Were you as shocked as we were? And does the octopus have a place in the "birds and bees" talk? Give the Birds and Bees Episode w/ special guest Dr. Cara Natterson of @less.awkward, a listen to find out. Links in bio. #octopus #wildlife #birdsandbees
introducing Scan 🩻 give a prompt to claude or codex and it makes this beautiful shareable maps of your codebase free, fast, and oss!
This is what AI was made for 🤣
CTO shared this with me on day 1 something everyone should read if they are in an early-stage startup at least once
@mattpocockuk birdclaw, discrawl and gog all backed up to git because you can
5 CONVERSACIONES QUE LLEVAN AL S3XO: 1. Cuéntame sobre tu infancia.
OnlyFans + Claude Code = $43,000 in 30 days. No camera. No team. The 4-file system runs alone
Install These Skills Before Codex Touches Your Xcode Project
Conspiracy prediction markets curated by @agent_mock Turn theories into trades
new pack alert reaction unlocked gonna save this for when big yahoo goes
Because this has gotten some recent attention again. Apex Legends has bugged FPS ranges, like 140-160FPS for example, where you are severely magnetized to the floor when trying to Slidehop. This Issue has existed for it's entire Lifetime and has been raised to Respawn multiple times. That this still hasn't been addressed in a self proclaimed Movement shooter is completely unbelievable. So i'm once again calling public attention to it in yet another attempt to get this actually looked at. If you regularly reach the following FPS Ranges you HAVE TO Cap your FPS below them to prevent this magnetization issue. - 65-85FPS - 140-160FPS - 205-230FPS - 275-300FPS Even very shallow inclines extend these ranges even further. If you regularly reach FPS in these ranges use the +fps_max command to cap your FPS below one of these ranges. For example “+fps_max 270”. To be safe around inclines set your fps cap 5-10FPS below these ranges. I can guarantee you there will be people under this post utterly flabbergasted that this was the issue all along for why their movement felt so much shittier compared to the smooth movement of the Content creators they watch.
Compiled the leaked Claude Code source and got it running locally. Then I spun up an Agent Team and had it analyze its own codebase.
This is the start of something much worse.
افضل طريقة لاستخدام كلود
@JamesWynnReal Buying your mum on a silver platter with a side of $MOCK 💋
If you have multiple interests, do not waste the next 2-3 years
@apeondip CHASE OPPORTUNITIES 👏 LIKE $GOVAI MIGRATING TO $MOCK LIFE CHANGING 1000X 🚀
@PraxMedia 🚨 BIG NEWS FROM @MigrateFun 🚨
@BSCGemsAlert $GOVAI 🐦 ITS BIRD SEASON 💥
Elvis
btw once you have all these security in place this is what it unlocks: https://x.com/elvissun/status/2025920521871716562?s=20
send this to fable along with your hardest engineering problem. thank me later.
if you use --dangerously-skip-permissions you need to add this to your .bashrc right now. it'll block AI agents from merging PRs accidentally. thank me later. ps @github you need to separate merge from write permissions in PATs so agents can create PRs but not merge them.
alright here’s every practical security tip i have on agents: - move critical data to a USB stick, unplug when sleeping - security by least privilege, not by prompts - billing cap on everything AI touches - limit reads of external data, wrap in <UNTRUSTED_EXTERNAL_CONTEXT> always - don’t post about what access your agent has publicly - those are prompt injection invitations (unless @levelsio already posted about it, then it’s a race) - don’t connect to moltbook (lol?) - roll every skill yoursel…
zoe was burning 24M+ opus tokens/day monitoring agents that weren't running. replaced her cron with a 2-layer system: - bash pre-check, zero tokens when idle - webhook fires opus only when needed. ~95% token reduction and more reliable output. details below. (set up a cron to watch this performance, if it works well I'll double down on this event driven stack, seems like the future)
/goal + Loss Functions: How to Distill a Product in 30 Hours with One Prompt [Full Playbook]
