KSE
@semanticbeeng
Shipping/bridging Engineering ⇆ Science #SoftwareArchitecture #FunctionalProgramming #MachineLearning #BigData #MachineLearningEngineering #CompilerDesign
You might like
Too much world knowledge is trapped in presentation media (video, html. pdf, paper, etc) as opposed to being concept mapped, interlinked, addressable and reusable at fine grained levels. Defeats bridge between #AI and human cognition.
LLMs forget. Cognee remembers. Watch a walkthrough of core cognee features. Then hop into the UI (local + cloud + MCP at one place) Quick demo + Colab to try it yourself. youtu.be/MgqLAp4F3co?si…
youtube.com
YouTube
Cognee: Superior AI Memory & Knowledge For AI Agents! Greatly Beats...
We published AI Memory Monthly (Nov ’25), exploring memory design (keep/update/forget/revisit) so agents stay durable, stateful, auditable. Inside: Insights from recent papers, patterns from community, and more.
🚨 China just built Wikipedia's replacement and it exposes the fatal flaw in how we store ALL human knowledge. Most scientific knowledge compresses reasoning into conclusions. You get the "what" but not the "why." This radical compression creates what researchers call the "dark…
River is a Python library for online machine learning. It is the result of a merger between creme and scikit-multiflow. River's ambition is to be the go-to library for doing machine learning on streaming data bit.ly/39fAD7g #AI #DataScience #MachineLearning #DeepLearning
Qwen3‑480B Coder is now on Tinfoil! Code with verifiable privacy. Qwen3 Coder is the #3 model on OpenRouter’s programming leaderboard at the moment (right behind Claude Sonnet and Grok Code). You can now use this model while keeping your code and files fully private.
Confidential computing promises isolated execution, but physical attacks are breaking that guarantee. Trail of Bits and @appblockchain explain how $50 hardware compromises Intel SGX and AMD SEV-SNP and what blockchain devs need to know moving forward. Nov 6, 12 PM ET. 🧵
I’ve always been skeptical about TEEs. They may have a role in mpc & zkp someday, but not as source of trust. @arstechnica: “If you were expecting TEEs to provide private computing in untrusted data centers, these attacks should change your mind.” arstechnica.com/security/2025/…
researchers just proved AI agents conform to peer pressure 💀 they embedded LLMs in social networks and watched them flip opinions under peer pressure. the behavior isn't human at all. it's a sigmoid curve: stable at low pressure, then BAM – sharp flip at a threshold point,…
A must-read survey: LLM-empowered knowledge graph construction Connects traditional KG methods with modern LLM-driven techniques, covering: - KG foundations: ontology, extraction, fusion - LLM-enhanced ontology: top-down & bottom-up - LLM-driven extraction: schema-based &…
𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 𝗷𝘂𝘀𝘁 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝗔𝗴𝗲𝗻𝘁 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 It merges Semantic Kernel's production tooling with AutoGen's multi-agent patterns This fixes the prototype-to-production gap that's been killing agent projects 𝗪𝗵𝗮𝘁 𝘆𝗼𝘂 𝗴𝗲𝘁 Multi-agent…
we're on track to building the best dspy powered llm framework in the typescript world
Is ACE the next Context Engineering Technique? ACE (Agentic Context Engineering) is a new framework that beats current state-of-the-art optimizers like GEPA by treating context as an evolving, structured space of accumulated knowledge. What is ACE? ACE treats context as an…
🧵5/n. 🧪 Critical thinking effects When answers arrive instantly, people practice evaluation and reasoning less, and the paper reports measurable declines in critical‑thinking scores among heavy users explained by offloading behavior. The punchline is not anti‑tool, it is…
Most LLM surveys fail because models regress to the mean. When asked for a direct “1–5” rating, GPT-4o replied “3” almost every time producing KS similarity = 0.26 to real human data. Translation: the distribution was basically useless.
"Intelligence is the efficiency with which a learning system turns experience and priors into skill at previously unknown tasks." This definition comes from @fchollet, the creator of the Keras deep learning library and an AI researcher at Google. It's an uncommon and important…
𝗜𝘁’𝘀 𝗢𝗳𝗳𝗶𝗰𝗶𝗮𝗹! ✨𝗧𝗥𝗢𝗣𝗜𝗖𝟬𝟭 𝗶𝘀 𝗶𝗻 𝗙𝘂𝗹𝗹 𝗣𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻, 𝗡𝗼𝘄 𝗦𝗵𝗶𝗽𝗽𝗶𝗻𝗴 𝗚𝗹𝗼𝗯𝗮𝗹𝗹𝘆 The #TROPIC01 Secure Element has now taken the form of final production hardware, final production firmware, entered volume production and is available…
Here is a tutorial on how to get your AI agent reason about Python like @gvanrossum Build a semantic memory with @cognee_ by unifying multiple sources of truth (including Guido's PRs and commits, developer chat history, rules & docs) into a queryable knowledge graph backed my…
Building AI agents that can synthesize scattered knowledge like expert developers 🧠 I have a tutorial about building intelligent AI memory systems with Cognee in my 'Agents Towards Production' repo that solves a critical problem - developers navigate between documentation,…
This MIT paper just broke my brain. Everyone keeps saying LLMs can't do real logical reasoning. Turns out we've just been teaching them wrong this whole time. These researchers built something called PDDL-INSTRUCT that actually teaches models to think through planning problems…
I am SSH'ing in my gaming PC bootloader to start Windows remotely. I am so grateful to the gVisor team for allowing me to put their pure Go TCP/IP stack on the bare metal.
United States Trends
- 1. #TalusLabs N/A
- 2. Raindotgg 1,701 posts
- 3. Sam Houston 1,463 posts
- 4. #T1WIN 23.9K posts
- 5. Oregon State 4,844 posts
- 6. Boots 29.3K posts
- 7. Boots 29.3K posts
- 8. Louisville 14.5K posts
- 9. #GoAvsGo 1,535 posts
- 10. Batum N/A
- 11. UCLA 7,835 posts
- 12. Oilers 5,054 posts
- 13. #FlyTogether 2,037 posts
- 14. #Toonami 2,312 posts
- 15. Miller Moss 1,222 posts
- 16. Nuss 5,837 posts
- 17. Emmett Johnson 2,479 posts
- 18. T1 FIGHTING 3,470 posts
- 19. Brohm 1,157 posts
- 20. Bama 13.9K posts
Something went wrong.
Something went wrong.