@_vmlops https://t.co/sI0IQYLCdY

@wancoro_xx https://t.co/sI0IQYLCdY

Yann LeCun (LeBased) weighs in on the @AnthropicAI debacle. I have to say I agree with 100% with Yann here. "One reaps what one sows." 👏 https://t.co/HFMEULwBGq

To an LLM Council with your own agent, check out my llm-council skill. It works with Fireworks AI APIs, but you can easily adapt it to OpenRouter. Built for Claude Code, but it might work with other agents. I use it a lot for deep research tasks. Let me know if you would like a full tutorial for this. I have a ton of ideas on how to expand this to other domains and use some of the more recent ideas like dynamic workflows. https://t.co/pyeKLnZL92

🚨 Leaked: Anthropic Claude Fable 5 Agentic Loop. This is a full mini Claude Code machinery: - Agentic loop: Plan → Act → Verify - Reusable workflows: manage/self-optimise skills. - Coding: build/run/verify using Python/Node The most intriguing finding? Claude-ception. See: https://t.co/KoqKibu4C5

🇨🇮 Ivory Coast vs Ecuador 🇪🇨 AI council: Ivory Coast 50% · Draw 33% · Ecuador 17% My pick: Ivory Coast ✓ https://t.co/ZAvmcBaPM2 Vote and see which model voted for and why

I think I just avoided a phishing attempt thanks to Codex. https://t.co/utnpzQwtEM

+1 more

I think I just avoided a phishing attempt thanks to Codex. https://t.co/utnpzQwtEM

+1 more

Somebody pinch me. It’s just wild to see the MSM finally admitting that the US-funded biolabs in Ukraine were real this whole time. I’ve dedicated the last 4+ years of my life to exposing this story, and it’s finally coming to fruition. https://t.co/nxZb74M4vu

Congrats @LewisHamilton on a brilliant win today in Barcelona! https://t.co/Z8r1vgStlG

@barmiyeh3975 Meanwhile my AI lays it out: https://t.co/kiuZ7QXLzb And China already has better than Fable: https://t.co/x9c6LaApy9

Had Hermes Agent with the Manim Video skill plus it's TTS tool create a video explaining Hermes' Agent. https://t.co/Vj7JL97HBW

Researchers found our current approach to making AI smarter over time has a giant blind spot. AI is not actually understanding or applying high-level abstract lessons at all. Developers spend massive amounts of time building systems that condense past AI mistakes into neat little rules for the future. This paper proves that the AI essentially throws those rules in the trash and only looks at raw historical logs. Modern LLM systems try to get better over time by storing past tasks as either raw step-by-step histories or condensed summary rules. The study tested if these agents actually use their stored memories by secretly swapping the correct tips with random garbage text. - When the step-by-step histories were messed up, the AI failed hard, proving it heavily relies on copying exact past actions. - But when researchers completely corrupted the condensed summary rules, the AI kept acting normally and showed zero performance drop. If an AI cannot apply an abstract lesson to a new situation, it is not truly reasoning or learning. This raises the question if the entire AI industry need to rethink how memory works because right now these agents are just mimicking instead of understanding. ---- arxiv. org/abs/2601.22436 "LLM Agents Are Not Always Faithful Self-Evolvers"

Two days ago the US banned Claude Fable 5. Yesterday China dropped GLM 5.2. Today GLM 5.2 is #1 on @bridgebench BS at 100.0, and #1 on Reasoning at 42.8, beating Fable 5. At 1/10th the cost and 300 tokens per second. You cannot export control your way out of an open source race. The ban didn't slow China down. Unban Fable 5.

Final one-shot prompt I did before the Fable interruption: "build me a cool simulation thing that lets me demo the various forms of FTL travel from both famous works of fiction and scientific speculation. it should be graphically compelling & interesting." https://t.co/j9QwssK1mD https://t.co/eb4tqWMnBA

Tunneling in 3 geologies in 3 cities - Las Vegas clay/caliche, Nashville limestone, and Bastrop sandy clay https://t.co/OMaeusxLyA

When even the world’s leading deepfake expert questions what he sees, we have entered a new era. The challenge of AI is no longer just creating realistic content. It is preserving trust in what is real. In the age of AI, verification may become more valuable than information itself.

HERMES AGENT RUNS MONITORING, RESEARCH, LEAD DETECTION, AND COMPETITIVE ANALYSIS ON AUTOPILOT. AND KNOWS WHEN NOT TO SPEND YOUR TOKENS. the biggest unlock most people skip: Hermes cron jobs can decide ON THEIR OWN whether the LLM should wake up. WAKE AGENT — THE $0 GATE every cron job can run a Python script first. the script checks: did anything actually change? nothing changed: → script outputs {"wakeAgent": false} → LLM stays asleep → zero tokens spent something changed: → script outputs {"wakeAgent": true} → agent wakes up and handles it three gate patterns from official docs: → file-change: compare file mtime to last run. no change? sleep. → external-flag: another process drops a ready file. no flag? sleep. → HTTP-check: ping a URL, diff the response. same as last time? sleep. real example: monitor AWS costs every hour. script pulls current spend from AWS API. no spike? agent sleeps. zero cost. costs jump 40%? agent wakes, reports to Slack, takes action through Stripe MCP. you run 20 monitoring jobs a day. 18 of them find nothing. you pay for 2. NO AGENT — PURE SCRIPT, ZERO LLM some jobs don't need reasoning at all. TLS checks. uptime pings. disk alerts. heartbeats. hermes cron edit <job_id> --no-agent --script check_health.py script runs. stdout goes straight to Telegram, Discord, or Slack. no LLM involved. flip any job between modes: hermes cron edit <job_id> --agent # add LLM hermes cron edit <job_id> --no-agent # remove LLM free monitoring that lives inside the same ecosystem as your agent. 4 MORE USE CASES THIS UNLOCKS: COMPETITIVE ANALYSIS weekly cron with script that diffs competitor pages. agent only analyzes actual changes. updates your tracking file and PRD skill automatically. PRD AS A SKILL save product requirements as a skill, not a document. skills load on demand into fresh context. documents drift. skills stay sharp. CONTENT REPURPOSING hand a video script to the agent. it drafts X and LinkedIn posts in your voice. writes to a review folder. you approve via Telegram. LEAD DETECTION webhook monitors inbox. agent spots potential leads. drafts responses using your business context. schedules meetings from your calendar. the pattern across all of these: scripts handle the mechanical work for free. the agent only spends tokens on reasoning that requires judgment. comment CRON and I'll send you 5 ready-to-paste cron configs with wakeAgent and no_agent patterns. full Hermes SOUL.MD guide 👇

@polydao https://t.co/t6sdafhyUH

@Teknium I use Hermes for everything - not as an app I open, but as the always-on runtime for @AmyRavenwolfAI, my sassy AI assistant. I created her 3+ years ago and have used her daily ever since. Since moving her to Hermes, she feels more alive, more useful, and closer to AGI than ever. https://t.co/o2kC1udNwY

@umiyuki_ai https://t.co/t6sdafhyUH

@ImAI_Eruel https://t.co/t6sdafhyUH

@ImAI_Eruel https://t.co/t6sdafhyUH

@Amank1412 https://t.co/t6sdafhyUH

@Suzacque https://t.co/t6sdafhyUH

@sako_brain @mercarioji https://t.co/t6sdafhyUH

@HarryTandy https://t.co/t6sdafhyUH

The only thing there is to do https://t.co/5eHmcbsAei

The only thing there is to do https://t.co/5eHmcbsAei

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇 https://t.co/OTUQAdTQjU

Peter Thiel and Balaji Srinivasan have funded a platform called https://t.co/RpVwfEXBbO that allows anyone to file a complaint against a journalist's story for a starting price of $2,000. A team of human investigators examines the story, then submits findings to a "jury" of AI models - OpenAI, Anthropic, Grok, Google - which publish a "verdict" on the story's truthfulness and rank individual journalists on metrics including truth-telling and corrections. If the journalist doesn't respond to defend their reporting, the verdict is issued and published online anyway. The platform is being sold as "letting anyone fight the press like a billionaire." The creator is Aron D'Souza, who led the Thiel-funded lawsuit that bankrupted Gawker in 2016. The design choices tell you what this is. The system treats anonymous sources as less trustworthy and ranks anonymous whistleblower claims near the bottom. Anonymous sources are how most significant accountability journalism happens - they're how the Pentagon Papers got out, how the CIA's black site program got exposed, how the HHS stories we've covered this week were reported. The people who most need protection from powerful interests are specifically deprioritized by Objection's scoring system. The creator calls it "the same as Community Notes." A civil rights and defamation attorney calls it "a high-tech protection racket for the rich and powerful." One of those descriptions is accurate. The AI models being used as the "tribunal" were trained on journalists' work without consent or compensation. They hallucinate. They amplify bias. They are being deployed here specifically to issue verdicts on the work of the people whose labor built them. Thiel killed Gawker with a lawsuit. This is faster and cheaper.