Evaluations: Trust, performance, and price (bonus, announcing RewardBench) | allainews.com

March 20, 2024, 6:39 p.m. | Nathan Lambert

Interconnects www.interconnects.ai

Evaluation is not only getting harder with modern LLMs, it’s getting harder because it means something different.

bonus evaluation llms modern performance price something trust

More from www.interconnects.ai / Interconnects

How RLHF works, part 2: A thin line between useful and lobotomized 5 days, 3 hours ago | www.interconnects.ai

beyond chat evaluation fine-tuning +5

Phi 3 and Arctic: Outlier LMs are hints 6 days, 18 hours ago | www.interconnects.ai

arctic industry llms lms +3

AGI is what you want it to be 1 week, 5 days ago | www.interconnects.ai

agi definitions people

WIP Llama 3: Scaling open LLMs 2 weeks, 4 days ago | www.interconnects.ai

article llama llama 3 llms +3

Stop "reinventing" everything to solve alignment 2 weeks, 5 days ago | www.interconnects.ai

alignment computing everything feedback +7

The end of the “best open LLM” 3 weeks ago | www.interconnects.ai

compute llm llms modeling +2

We disagree on what open-source AI should mean 1 month ago | www.interconnects.ai

mean multiple open-source ai people +3

DBRX: The new best open model and Databricks’ ML strategy 1 month, 1 week ago | www.interconnects.ai

70b databricks llama llama 2 +4

Evaluations: Trust, performance, and price (bonus, announcing RewardBench) 1 month, 2 weeks ago | www.interconnects.ai

bonus evaluation llms modern +4

Founding AI Engineer, Agents

@ Occam AI | New York

View on ai-jobs.net

AI Engineer Intern, Agents

@ Occam AI | US

View on ai-jobs.net

AI Research Scientist

@ Vara | Berlin, Germany and Remote

View on ai-jobs.net

Data Architect

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

View on ai-jobs.net

Data Engineer

@ Kaseya | Bengaluru, Karnataka, India

View on ai-jobs.net