getting something right is, again, not the same as not hallucinating. There are multiple sources of error; whole cloth inventions are different eg from misparsing of instructions. Databases don’t just invent things but LLMs do.
LLMS
-
AI Honesty Over Arbitrary Problem-Solving Capabilities
By
–
It seemed to me that the interesting claim was not that AIs would start getting arbitrary problems right, but that AIs would in nearly full generality stop making stuff up if they didn't know.
-
How GPT Works Explained Using Jane Austen Examples
By
–
Let Us Show You How GPT Works — Using Jane Austen https://
nyti.ms/3ItZUNg
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
GPT 4.5 Outperforming Professionals Would Change Skeptics’ Minds
By
–
I bet you'd change your tune after the third time GPT 4.5 solved a problem that stumped your doctor / electrician / plumber.
-
H2O Celebrates h2ogpt Falcon-7B Win in LLM Democratization
By
–
Thrilled to see the positive feedback from the community, especially when it comes to something we are deeply passionate about @h2oai
: Democratizing #LLMs. The winner is h2ogpt falcon-7b model: https://
youtu.be/1yHNth_yzcw via @YouTube -
Semantic Search Edge Cases and LangChain Mitigation Methods
By
–
I participated in a fun webinar with @zilliz_universe on Thursday where I talked about retrieval We did a deep dive on edge cases that arise with semantic search, and methods in LangChain to mitigate those Here are the slides: https://
docs.google.com/presentation/d
/1NHWOLnaA6qhwus3JbluBk7aN1HeKrobZuaRNEdEZSkU/edit?usp=sharing
… -
Bet on AI Hallucinations Elimination by June 2025
By
–
We’re agreeing now right? So you bet against my claim that by June 2025, hallucinations will be largely eliminated meaning that 95% of the time generations will be verifiably accurate… and therefore reliable and useful causing profound transformations
-
Take a Break: Understanding LLMs YouTube Video Coming Soon
By
–
Starting soon: https://
youtube.com/watch?v=Ycbi4u
XJq4k&ab_channel=AbhishekThakur
…
Take a break from not understanding LLMs -
PandaGPT: Multimodal AI Model for Vision, Audio, Text Tasks
By
–
PandaGPT is a general-purpose instruction-following model that can both see and hear. PandaGPT can perform complex tasks such as detailed image description generation, writing stories inspired by videos, and answering questions about audios. https://
bit.ly/45TnAVl -
AI Research Highlights: LLM Optimizers and Vision Transformer Scaling Laws
By
–
It's been a another wild month in AI & Deep Learning research. I curated and summarized noteworthy papers here: https://
magazine.sebastianraschka.com/p/ai-research-
highlights-in-3-sentences-2a1/
… Ranging from new optimizers for LLMs to new scaling laws for vision transformers.