New book from @PacktDataML >> "Building AI Agents with LLMs, RAG, and Knowledge Graphs — A practical guide to autonomous and modern AI agents" See it at http://
amzn.to/4622k2h
LLMS
-
New Book: Building AI Agents with LLMs, RAG, Knowledge Graphs
By
–
-
New Packt Book on Enterprise Generative AI Systems
By
–
New release from @PacktDataML >> "Building Business-Ready Generative #AI Systems — Build Human-Centered Generative AI Systems with Context-Aware Agents, Memory, and LLMs for the Enterprise" See it at http://
amzn.to/3Jdcio5 -
Cursor Improves Tab Model with Online Reinforcement Learning
By
–
We've trained a new Tab model that is now the default in Cursor.
— Cursor (@cursor_ai) 11 septembre 2025
This model makes 21% fewer suggestions than the previous model while having a 28% higher accept rate for the suggestions it makes.
Learn more about how we improved Tab with online RL. pic.twitter.com/WYTYaynnEIWe've trained a new Tab model that is now the default in Cursor. This model makes 21% fewer suggestions than the previous model while having a 28% higher accept rate for the suggestions it makes. Learn more about how we improved Tab with online RL.
-
Software Engineers Fear Hardware in Cloud-First LLM Era
By
–
the amount of people saying "just use an API bro" when it comes to LLMs is insane i get it, not everyone's into gpus or hardware; but do these people realize that we're in an era where Software Engineers are legit SCARED of hardware? everything's "in the cloud" now, vendors are
-
ChatGPT Inefficiency: Data and Compute Requirements Analysis
By
–
The more data and compute AI needs, the less smart it is. By which standard ChatGPT is mind-blowingly stupid.
-
Beyond Model Training: The Art of Prompt Engineering
By
–
I mean yes but not really. Everything after training the AI model (which I don't cause I don't have $100M lying around) is pretty much voodoo and prompting
-
Alibaba Releases Qwen3-Next-80B with Optimized Inference Performance
By
–
New on Poe: Qwen3-Next-80B! Alibaba’s latest model brings highly optimized inference → strong tokens/sec throughput + low latency, while still excelling on math & coding benchmarks. (1/2)
-
Qwen3-Next-80B LLM Now Available on Poe Platform
By
–
Qwen3-Next-80B is powered by
@novita_labs
. You can try it with thinking on/off at
https://
poe.com/Qwen3-Next-80B and
https://
poe.com/Qwen3-Next-80B
-Think
…, across all platforms, and through the Poe API in your favorite coding apps. (2/2) -
Large Models Opacity: We Become Audience Instead of Magician
By
–
Important insight about the opacity of large models: "…the issue with wizards: We're getting something magical, but we're also becoming the audience rather than the magician."
-
Deep Learning Math Limitations vs AI Mathematical Capabilities
By
–
Don’t confuse “deep learning can’t do math” with “AI can’t do math”. AI was born doing math.