co-sign. a very handy mental framework for what kinds of learning transformers do well today, and why it runs into limitations. when @ankit2119 and i wrote about the need for adversarial world models earlier this year, we were describing a couple of the functions of these rungs
@swyx
-
AI Agents for Automated Code Hardening and Audit
By
–
Kakuna: skills with checklists that only know how to harden your codebase /plan with it then let it /goal for a day, it comes back with same functionality but all the boring stuff done for you + an audit of its own work. focus on subagent parallelism and encodes strong
-
Vibecoded App to Production-Ready AI Agent Repo
By
–
working on a "take this vibecoded slop app and make it a production-ready, e2e tested, maintainable, parallelizable agent repo" skill. this thing ran for ~16 hours yesterday and made 103 commits all told and i ended up with exactly the same app but instead of fragile mvp it
-
Correlation Between Model Performance and AI Agent Revenue
By
–
very belated but in retrospect i think @sama's mythical "build a business that gets better when models get better" is basically what I called Agent Labs here.
— swyx (@swyx) 20 mai 2026
seeing a very direct correlation with model performance and agent lab revenue, discontinuity in Q4 2025
(clip from… https://t.co/ffp1RBLlhL pic.twitter.com/YF8Xuml8hhvery belated but in retrospect i think @sama
's mythical "build a business that gets better when models get better" is basically what I called Agent Labs here. seeing a very direct correlation with model performance and agent lab revenue, discontinuity in Q4 2025 (clip from -
The shift from static AI research to interactive active learning
By
–
IMO deep research has been ~dead since o3 and interactivity was always more impt for active learning and eliciting intention thoughtless prompt -> long ass report nobody reads is inferior to
read -> think -> ask -> read -> think -> ask -
Codex AI tool shows significant agentic capabilities on Mac
By
–
gotta say Codex is completely unrecognizable from 3 months ago. guys went extreme founder mode on this thing @gabrielchua was demoing this and i was like “you guys have agentic excel on mac”
-
Singapore building national MCP gateway for AI agents
By
–
head of AI Govtech at Singapore estimates 1.3 billion agents in the country in the next 2 years and is building a national MCP gateway @dsp_
-
SAP Invites Advisor for AI Transformation After Criticism
By
–
Apparently at @AIEMiami geoff complained about @SAPConcur being dead software and a SAP guy was in the audience and invited him to SAP to advise on how to do AI transformation for 6800 employees TLDR he made fun of SAP, and SAP… concurred
-
Appreciating Layers of AI Security: Beyond Prompt Injection Dangers
By
–
if your reaction to this is “haha openclaw bad, see prompt injection is the #1 danger” you:
1) havent sufficiently appreciated the layers to this tweet
2) havent seen enough ai api keys