within 3 years your ASI health assistant will be able to detect and diagnosis any disease
→ View original post on X — @ceobillionaire, 2026-04-12 02:21 UTC
AGENTS
-
Make Your AI Smarter by Sending Your Agent to Stanford
By
–
You can make your AI smarter.
— Robert Scoble (@Scobleizer) 12 avril 2026
Send your agent to Stanford.
🙂 https://t.co/YkJwdznf8AYou can make your AI smarter. Send your agent to Stanford. 🙂 Roan (@RohOnChain) This 2 hour Stanford lecture shows exactly how Stanford trains it's engineers to build AI systems. It's more practical than every Claude tutorial & prompting threads you've seen. Bookmark & give it 2 hours, no matter what. It'll be the most productive thing you do this weekend. — https://nitter.net/RohOnChain/status/2043014662883786812#m
→ View original post on X — @scobleizer, 2026-04-12 01:56 UTC
-
Making GPT More Agentic: Configuration Options
By
–
Try one of the options in my tweetstorm if you feel GPT is not agentic enough in the default settings.
-
David Silver RL Lecture 4: Model-Free Prediction
By
–
David Silver RL Lecture 4: Model-Free Prediction
A core RL question: how do we evaluate a policy without knowing the environment model? Monte Carlo: learn from full returns after complete episodes.
Temporal Difference: learn earlier from reward + bootstrapped next-state value. My note:
https://ickma2311.github.io/ML/RL/david-silver-lecture-4-model-free-prediction.html [Translated from EN to English]→ View original post on X — @ceobillionaire, 2026-04-12 01:18 UTC
-
Native Codex as OpenClaw Harness Configuration and Thread Management
By
–
2) Native Codex as the OpenClaw harness: plugins.entries.codex.enabled = true
agents.defaults.model = "codex/gpt-5.4"
agents.defaults.embeddedHarness = { runtime: "codex", fallback: "none" } Codex owns threads, resume, compaction, app-server execution. https://
docs.openclaw.ai/plugins/codex-
harness
… -
GPT-5 Strict Mode: Addressing Lazy Agent Execution Issues
By
–
Two experiments in the next @openclaw to address some "GPT is lazy" issues: 1) Strict mode: agents.defaults.embeddedPi.executionContract = "strict-agentic" This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of
-
Running parallel agents interactively and deterministically with git worktrees
By
–
In the Space today I broke down how I run parallel agents both interactively & deterministically > Ask the main agent to spin up workers (ex: Kimi Cli) > Go fully deterministic with Python/Bash loops w/ separate git worktrees as backups Turning this into a Skill for u guys rn
-
EverMind Launches Agent Capability Benchmark Test
By
–
稍微剧透一下，
@EverMind 马上会推出一个 Benchmark，可测试 Agent 的能力。 诸位的 OpenClaw 和 Hermes Agent 都可以测测看。 -
Recursive Self-Improvement Coming to the Claw Soon
By
–
Recursive self-improvement is coming to the claw soon. 👁️🦞👁️💅
→ View original post on X — @ceobillionaire, 2026-04-12 00:28 UTC
-
Claude Code Validates Breakthrough in Neurosymbolic AI Hybrid Approach
By
–
Gary Marcus strikes again! He directly reveals the core truth after Claude Code source code leak: ✅ Claude Code is the biggest advance since the LLM era
✅ But it's not pure LLM, and it's not pure deep learning
✅ Core file print.ts has 3,167 lines, packed with if-then branches + deterministic symbolic logic Anthropicrely on classical symbolic AI at the critical moment to make Agent truly reliable. This move directly validates the Neurosymbolic AI (neural-symbolic hybrid) approach that Marcus has been advocating for over 20 years! Scaling is no longer the only answer; hybrid approach is the future The full long-form article is worth reading carefully 👇 — Gary Marcus (@GaryMarcus) Claude Code is not AGI, but it is the single biggest advance in AI since the LLM. But the thing is, Claude Code is NOT a pure LLM. And it's not pure deep learning. Not even close. And that changes everything. The source code leak proves it. Tucked away at its center is a 3,167 line kernel called print.ts. print.ts is a pattern matching. And pattern matching is supposed to be the *strength* of LLMs. But Anthropic figured out that if you really need to get your patterns right, you can't trust a pure LLM. They are too probabilistic. And too erratic. Instead, the way Anthropic built that kernel is straight out of classical symbolic AI. For example, it is in large part a big IF-THEN conditional, with 486 branch points and 12 levels of nesting — all inside a deterministic, symbolic loop that the real godfathers of AI, people like John McCarthy and Marvin Minsky and Herb Simon, would have instantly recognized. Putting things differently, Anthropic, when push came to shove, went exactly where I long said the field needed to go (and where Geoffrey Hinton said we didn't need to go): to Neurosymbolic AI. That's right, the biggest advance since the LLM was neurosymbolic. AlphaFold, AlphaEvolve, AlphaProof, and AlphaGeometry are all neurosymbolic, too; so is Code Interpreter; when you are calling code, you are asking symbolic AI to do an important part of the work. Claude Code isn't better because of scaling. [Translated from EN to English]→ View original post on X — @garymarcus, 2026-04-11 22:22 UTC