try using o1 it's much better at finding all instances of a thing claude / gemini only good at finding a few
LLMS
-
Cerebras Inference: 2200 tokens/sec on Llama 3.3 70B
By
–
What will you build in 2025 with the world's fastest Inference?
— Cerebras (@cerebras) 19 décembre 2024
Cerebras Inference by the numbers:
🔥 Blazing fast 2200 tk/s on Llama 3.3 70B.
🏎️ Record-breaking 969 tk/s on Llama 3.1 405B.
👋 70x faster than GPUs.
Try it today: https://t.co/rHJozqZvAx pic.twitter.com/xjuvA5Ooh7What will you build in 2025 with the world's fastest Inference? Cerebras Inference by the numbers: Blazing fast 2200 tk/s on Llama 3.3 70B. Record-breaking 969 tk/s on Llama 3.1 405B. 70x faster than GPUs. Try it today: http://
chat.cerebras.ai -
ChatGPT accesses your tools: AI and No-Code revolution
By
–
New feature on #ChatGPT ChatGPT can access our tools, on our computer, and this is the first step of a revolution in AI automation and No-Code → https://youtu.be/W12AACYRrfk I show you everything in my latest video
-
Abacus AI: Enterprise-Grade Platform for Large-Scale AI Solutions
By
–
Explore @AbacusAI — https://
abacus.ai An #AI Brain for your Organization Trusted by Fortune 500 companies Leader in open-source AGI Research State-of-the-Art end-to-end AI Platform Large-Scale AI Solution with Enterprise Class Security #LLMOps and #MLOps -
2025: The Year of Agentic Systems – Key Practices Emerge
By
–
2025 will be the year of agentic systems The pieces are falling into place: computer use, MCP, improved tool use. It's time to start thinking about building these systems. At Anthropic, we're seeing a few best practices emerge – we wrote a blog post with our findings:
-
AI Giants Face Diminishing Returns in Cutting-Edge Development
By
–
and if you missed our previous story from *last month* that gives an in-depth look at how companies such as Google, OpenAI, and Anthropic are seeing diminishing returns from their efforts to build cutting-edge AI, give it a read! https://
bloomberg.com/news/articles/
2024-11-13/openai-google-and-anthropic-are-struggling-to-build-more-advanced-ai
… -
Google DeepMind Launches Gemini 2.0 Flash Thinking Model
By
–
Last announcement of the year from @GoogleDeepMind
? Not sure 🙂 but glad to be part of the team that launched Gemini 2.0 Flash Thinking, a model that is both smart & fast! Welcome to the Thinking era. What's next for 2025? Give Thinking a try at https://
aistudio.google.com/prompts/new_ch
at?model=gemini-2.0-flash-thinking-exp-1219
… -
Gemini 2.0 Flash Introduces Full CoT Traces
By
–
Gemini 2.0 Flash Thinking: Open AI has been Noam-ed! 👑
— Vaibhav (VB) Srivastav (@reach_vb) 19 décembre 2024
with FULL CoT Traces! pic.twitter.com/7ngPko3ZqvGemini 2.0 Flash Thinking: Open AI has been Noam-ed! with FULL CoT Traces!
-
Claude’s Targeted Artifact Edits Now Available for Specific Lines
By
–
We've also fully rolled out targeted Artifact edits – Claude can now modify specific lines instead of rewriting entire Artifacts (make sure the analysis tool is enabled to use this)
-
Using ChatGPT to generate formulas and code instead of Excel
By
–
L'intelligence artificielle a tué Excel ! Fini les formules complexes et les tutoriels YouTube de 15 heures. Voici comment vous pouvez créer des formules, des codes et des tableaux avec ChatGPT : [ Ajoutez en signet et RT pour ne pas perdre ! ]