The presence of AI writing is not itself an indication that a scientific paper is good, bad, or fraudulent. If we want AI to help accelerate science, we won’t do that without AI work “contaminating” journals. We should be doing more to say what good AI use in science looks like.
AI
-
Government Account Political Fundraising Raises Hatch Act Ethics Concerns
By
–
Process point: using a gov-affiliated account for political fundraising and mudslinging is, if my FTC ethics training memory serves, a Hatch Act violation. https://
x.com/jacobhelberg/s
/jacobhelberg/status/1767943760124784834
… -

Four Types of Data Analysis in Big Data and AI
By
–
Four types of #Data #Analysis
by @BoucherNicolas #BigData #ArtificialIntelligence #ML #MI #DataScience #Tech #Technology cc: @ravikikan @pbalakrishnarao @bigdata -
Chatbot Interface Design Limits Student Choice Paralysis
By
–
I built many game-like simulations for teaching & our early prototypes had students communicate with a human game master. For most people, having the option to do anything was paralyzing. It worked better when they were given choices. The chatbot interface has the same problem.
-
Memory Hackathon SF: LangChain MongoDB Anthropic LLM Applications
By
–
Memory Hackathon in SF with LangChain, @newcomputer
, @MongoDB and @AnthropicAI Sign up here: https://
lu.ma/taa6ijxt Long-term memory for LLM applications is one of the most interesting and important – yet also under explored – areas out there. We are THRILLED to be -

DUS SolarLLM Paper Accepted to NAACL 2024 Industry Track
By
–
Thrilled to announce that our DUS paper on #solarllm implementation has been accepted to the NAACL 2024 Industry Track! https://
openreview.net/forum?id=leEiE
v43Kz
… -

Cerebras Tackles GenAI’s Massive Compute and Memory Demands
By
–
At MemCon, Cerebras VP of Product Angela Yeung and EY's Global AI Innovation Officer Rodrigo Madanes unpacked GenAI's massive compute and memory demands. Training large AI models currently requires thousands of GPUs in order to store entire models in memory. Cerebras solves
-
LLM Language Constraints and Semantic Referent Loss
By
–
If the LLM does not represent enough constraints, its language can go "on holiday", i.e. lose its referent in an integrated model of the meaning universe. But so may the use of vague terms like "embodied in life" become superficial pattern matching without actual referent.
-
LLM Inference as Pattern Matching and Reasoning Process
By
–
The inference process of current LLMs is somewhat comparable to attempting to answer a question without deep analysis, ie through a process of pattern matching, creative association and constraint resolution. However, reasoning is itself a process of successive pattern matching.
-
Meaning as Universe Model Function and Representation
By
–
Meaning is the function that you use to model the entirety or your universe. Understanding the meaning of a representation is the establishment of relationships between that representation and the universe model.
