Your curated collection of saved posts and media
@ft_content https://t.co/sI0IQYLCdY
🚨 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: ht
@dair_ai https://t.co/sI0IQYLCdY
🚨 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: ht
@cryptorover https://t.co/sI0IQYLCdY
🚨 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: ht
To use 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
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
@cyrilXBT https://t.co/sI0IQYLCdY
🚨 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: ht
@ImAI_Eruel https://t.co/sI0IQYLCdY
🚨 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: ht
@RoundtableSpace https://t.co/sI0IQYLCdY
🚨 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: ht
@oikon48 https://t.co/sI0IQYLCdY
🚨 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: ht
@DavidSacks https://t.co/sI0IQYLCdY
🚨 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: ht
@kiyoshi_shin https://t.co/sI0IQYLCdY
🚨 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: ht
@antirez https://t.co/sI0IQYLCdY
🚨 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: ht
@jun_song https://t.co/sI0IQYLCdY
🚨 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: ht
@MTSlive @tomieinlove https://t.co/sI0IQYLCdY
🚨 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: ht
@xiathis https://t.co/sI0IQYLCdY
🚨 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: ht
@twetsfyp https://t.co/sI0IQYLCdY
🚨 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: ht
@_vmlops https://t.co/sI0IQYLCdY
🚨 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: ht
@wancoro_xx https://t.co/sI0IQYLCdY
🚨 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: ht
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
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
🚨 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
🚨Update: The difference in Claude Fable/Mythos is in paradigm. This family has a full agentic-loop, a micro Claude Code. The rest of the industry is still in chat mode. It can run for days unattended thanks to a sandbox with skills, memory & self-optimisation. Rabbit hol
🇨🇮 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
I think I just avoided a phishing attempt thanks to Codex. https://t.co/utnpzQwtEM
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
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 r
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