Grok 3 is launched on ChatLLLM!
LLMS
-
Upstage Information Extract: Agentic Document Data Extraction Without Training
By
–
Forget IDP. Agentic information extraction is here.
— Upstage (@upstageai) 10 avril 2025
Stop training models for every doc type. @upstageai Information Extract understands and extracts data from any complex document—invoices, resumes, contracts, medical forms—with zero training required.
API access is coming… pic.twitter.com/Acv5RcyABwForget IDP. Agentic information extraction is here. Stop training models for every doc type. @upstageai Information Extract understands and extracts data from any complex document—invoices, resumes, contracts, medical forms—with zero training required. API access is coming soon. Be among the first to try it. 👉🏻 Join the waitlist: upstage.ai/products/informat… 🧪 Try the live demo: console.upstage.ai/playgroun… 📄 Step-by-step usage guide: upstage.ai/blog/en/demo-now-…
-
CodeLLM Autocomplete Feature Now Supports Python React TypeScript
By
–
Loving the new autocomplete on CodeLLM You can vibe code Python, React and Typescrpt with ease
-
Cerebras Customers Already Running 128k Token Models
By
–
yes – already have customers using 128k on cerebras
-
New LLM Agent Quickstart with MCP Tools and Context Management
By
–
We just published a new quickstart – a minimal implementation of an LLM agent with MCP tools, loops, context management, based off principles from our Building Effective Agents blog post. Very helpful if you're trying to learn what an agent actually looks like in code!
-
OpenAI Releases BrowseComp Benchmark with Dataset and Paper
By
–
Check out the blog post here: https://
openai.com/index/browseco
mp/
…
Dataset here: https://
github.com/openai/simple-
evals
…
And the paper here: https://
cdn.openai.com/pdf/5e10f4ab-d
6f7-442e-9508-59515c65e35d/browsecomp.pdf
… Also thank you to the contributors on this benchmark, especially @EdwardSun0909 and @mia_glaese
! -
Hugging Face Partnership Enables Real-Time AI Agents and Code Generation
By
–
Our partnership with @huggingface allows developers to unlock new possibilities for real-time agents, code-generation tools, multilingual assistants, and more. Get instant access to the fastest open-weight inference on the planet—including @AIatMeta Llama 4 on the Cerebras
-
OpenAI Introduces Moonshine Memory Feature for Conversations
By
–
OpenAI is rolling out “Moonshine”, an improved memory that can refer to past conversations. https://t.co/B5SbZqKL4y pic.twitter.com/3ArF0TZBme
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 avril 2025OpenAI is rolling out “Moonshine”, an improved memory that can refer to past conversations.
-
LLMs Discover New Molecules for Medicine Development
By
–
Can LLMs help us discover the right molecules for new medicines? An MIT-led approach combines an LLM w/graph-based models to create new molecules w/specific properties. Users can request molecules in plain language & get a description of how to make it: https://
bit.ly/3RerIZY -
2.5-pro-experimental: Planning capabilities but struggles with bug fixing
By
–
ooo nice. 2.5-pro-experimental right? i find it just plans loads of stuff and hasn't been great with my bug fixing but i know its definitely user issue