Tbh this is pretty reasonable. Another axis of scaling:

This is a dev post classified by Jev as Security (an opinion), kept by the Dev Radar because it carries real work, not commentary.

Tbh this is pretty reasonable. Another axis of scaling: the size and quality of the in-context prior.

Posted by Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) (76.5k followers) 2 h ago · 3 likes · 1.2k views · view the original post on X. Kept by the Dev Radar as Security. Tools mentioned: cl4r1t4s.

More dev work like this

• rogue agents and prompt injection are currently considered the biggest unresolved threat… — @cantinasecurity
• Slashy for enterprise I don’t publicly talk about often — @GaddipatiHarsha
• Excited to continue pushing out talks and discussions from our Open Source AI Summit! — @PresidioBitcoin
• Cyber attackers move fast, so defenders have to move faster 🚨 — @cerebras
• We're excited to be in Okta's XAA, allowing AI agents to securely gain scoped access to… — @browserbase
• 🚰 SYSTEM PROMPT LEAK 🚰 — @elder_plinius
• METR’s vibe-coded dashboard exposed an agent through an authentication flaw. — @AlphaSignalAI
• our next “on M, DD, YYYY” drop, from two of the random guys, is probably the most… — @S1r1u5_

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 04:56 UTC. Full method.