Working with Apps Beta also includes a VSCode extension that allows ChatGPT to access editor context more reliably! It can also see selected parts of the code.
LLMS
-
Gemini Leads Chat Arena: Competitive AI Model Benchmarking
By
–
Nice and all, but Gemini still took first place on chat arena. Come on, you have more than just this.
-
LLMs Optimized for Agentic Workflows Boost Performance
By
–
Large language models (LLMs) are typically optimized to answer peoples’ questions. But there is a trend toward models also being optimized to fit into agentic workflows. This will give a huge boost to agentic performance! Following ChatGPT’s breakaway success at answering
-
Nexusflow Releases Athene v2 72B Competitive Model
By
–
Nexusflow released Athene v2 72B – competetive with GPT4o & Llama 3.1 405B Chat, Code and Math > Arena Hard: GPT4o (84.9) vs Athene v2 (77.9) vs L3.1 405B (69.3) > Bigcode-Bench Hard: GPT4o (30.8) vs Athene v2 (31.4) vs L3.1 405B (26.4) > MATH: GPT4o (76.6) vs Athene v2
-
Small Language Models Era: Efficiency and Accuracy at Scale
By
–
We're in our #small model era And, it's not just us. If you look at any organization seriously deploying GenAI at #scale, you'll find that they are adopting small specialized models (#SLMs) to unlock better efficiency and #accuracy. Check out our latest discussion with
-
OpenAI Questioned About Gemini Beating ChatGPT on LMSYS
By
–
@OpenAI how could you let this happen? Gemini took first place on lmsys overall. Any answer to this today? 🙂
-
Anthropic Workbench Enhances Prompts with COT
By
–
BREAKING 🚨: Anthropic Workbench got a prompt improvement feature based on a new COT reasoning implementation 🔥 https://t.co/sqHGib1meo pic.twitter.com/O5SyQ6xjud
— 🚨 AI News | TestingCatalog (@testingcatalog) 14 novembre 2024BREAKING: Anthropic Workbench introduces a prompt improvement feature powered by a new COT reasoning implementation
-
Claude optimizes prompts in under one minute through Workbench
By
–
Finally, Claude returns your optimized prompt that you can then test and iterate on in the Workbench. The entire process happens in less than a minute.
