It is weird how effective it is to apply human-inspired approaches to problem solving to help LLMs “think” better. Here, asking the AI to visualize each step in a navigation problem by drawing diagrams helps greatly improve performance on the problem.
LLMS
-
Token consumption surprisingly high for this thing
By
–
you may be surprised haha. thing chews tokens like a mf
-
Devin’s Real Innovation: Infrastructure, LLM Stack, and Agent UI/UX
By
–
i havent personally used that one yet so i cant opine (see how this works?) to me the devin innovation is excellent infra, and tasteful/creative combination of LLM OS stack, but what strikes me the most is in the async agent ui/ux. swebench is just a vanity metric. because of
-
Multiple LLM Agents Debate to Improve AI Performance
By
–
You could improve AI performance through all sorts of clever techniques… or you could just have more LLM agents try to solve the problem and debate amongst themselves as to which is the right answer. It turns out that adding more agents seems to help all AIs with most problems.
-
Grok chatbot generates fake headlines, LLMs prone to confabulation
By
–
.
@mattbinder reports on fake headline on eX-twitter generated by its chatbot Grok, and how more information here will be generated by an LLM which is, as one must expect if one knows how LLMs work, an avid confabulator (others call it hallucination). As often, hubris about the -
DSPy and LangChain Collaboration for LLM Optimization
By
–
Optimization of LLM Systems with DSPy and LangChain Recording from our webinar with @hwchase17 and @lateinteraction is up! Covers: Introduction to DSPy
Similarities to LangChain and most excitingly…
How LangChain DSPy can collaborate! https://
youtu.be/4EXOmWeqXRc -
AI Agents: Building and Hosting LLM Applications at Scale
By
–
#AI Agents – Build and Host LLM Apps At Scale
by @abacusai @nandishtella Read more: https://
buff.ly/3R3L83l #BigData #MachineLearning #ArtificialIntelligence #ML #MI cc: @patrickgunz_ch @yvesmulkers @ravikikan -
Agentic Stock Analysis Tool with Langchain and Claude
By
–
Building an Agentic Stock Analysis Tool with Langchain, OpenBB, and Claude 3 Opus A great article that touches on: Custom Tool Creation
Deploying with LangServe
Prompting strategies Full OSS code! https://
sethhobson.com/2024/03/buildi
ng-an-agentic-stock-analysis-tool-with-langchain-openbb-and-claude-3-opus/
… -
LLMs Limitations in Creating Shared Useful Abstractions
By
–
Fictitious entities yes of course. Fictitious entities that become new useful abstractions that everyone talks about, and everyone has a common understanding of them (ie shared): no. Also LLMs don’t spend much time asking people questions so they can learn useful new things to
-
Optimizing LLM Systems Beyond Model Performance
By
–
So much of the conversation focuses on the performance of large language models. Often, you can see a much bigger lift in performance by optimizing other LLM system components.
— Snorkel AI (@SnorkelAI) 6 avril 2024
Learn more in our latest case study video: https://t.co/ldCCYmHqOI #enterpriseai #llm #llmsystems pic.twitter.com/OD2OzXQHGvSo much of the conversation focuses on the performance of large language models. Often, you can see a much bigger lift in performance by optimizing other LLM system components. Learn more in our latest case study video: https://
youtu.be/09PIGmG8XiY #enterpriseai #llm #llmsystems