After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
Photon costs $0.23 to run a full competitor GEO audit.
Checks ChatGPT, Gemini, Perplexity, and Claude simultaneously.
Finds every citation gap.
Takes 3 minutes.
A GEO agency charges £2,800/month for a quarterly version.
The difference isn't quality. It's the salary of the team they built before the API existed.
Fable 5 is INSANE for creating ads
i built an agent that studies your competition and thousands of viral ads, then gives you a full viral blueprint for your brand to copy
just feed it a product photo and a landing page link and competitors names, 3 minutes later you've got a proven creative playbook for your ads, here's how it works:
- scans your brand's own website (copy, offers, structure, CTAs)
- scans competitor websites (you list them, or Claude finds likely ones for you)
- pulls live ad data straight from Meta Ad Library + TikTok via spytools
- extracts proven hooks, scripts, and visual/creative patterns from every source
- synthesizes everything into one swipe-file library
- output is a ready-to-paste doc, drop it into Claude and generate new ad scripts from proven angles instantly
- runs locally, one command, your own API keys, no video generation step slowing you down
runs 100% local, without $300/mo on spytool subscriptions or agency fees, full control, and API cost only
RT + reply w/ "AGENT" and i'll send it to you so you can use it for your brand (must follow so i can DM)
@papercliping just shipped document locks for AI agents.
Sounds minor. It isn't.
Thread on why governance features matter more than capability features right now:
🧵
The pattern: every wave of AI capability gets followed by a wave of governance tooling.
Claude got safety guardrails. Agents got observability. Multi-agent systems are getting document-level controls.
If you're deploying agents in production, governance isn't overhead. It's the feature.
New open-source agent: before you type a single prompt, it reads your Gmail, GitHub, Slack, Notion, Stripe, and 113 other services.
Builds a model of your entire work life. Locally. Offline.
7,800 GitHub stars in 7 days.
🧵
Still: the architecture is the insight. Watch what this approach becomes when security catches up to the vision.
For operators building with agents - the question this raises: what would your agents do differently if they had complete context from day one?