#dailyreport — Public Fediverse posts

Title: P4: Prompt-engineering CoT [2024-11-20 Wed]
powerful decoder. The discrete nature of VQ-VAE ensures
that the latent variables are not collapsed and are
actively used in the model.
- - - - - - - - - - - - - - - - - -
I published calendar with holidays and biggest conferences
for Emacs at MELPA for 2024 and 2025. I am going to
maintain this calendar to promote EmacsConf, FOSDEM and
AI conferences.
蠡 #dailyreport #promptengineering #vae #recsys #emacs

Title: P3: Prompt-engineering CoT [2024-11-20 Wed]
It's application are “Recomendation Systems with
Generative Retrieval” https://arxiv.org/pdf/2305.05065
that use Transformer model with embedding retrival for
RecSys.

In contrast to continuous VAEs, QV-VAE uses discrete
latent representation of a finite set of learned
embeddings.
VQ-VAE avoids the issue of "posterior collapse" often seen
in VAEs, where the latent variables are ignored by a #dailyreport #promptengineering #vae #recsys #emacs

Title: P2: Prompt-engineering CoT [2024-11-20 Wed]
more.
- CoT prompting constrains the model to follow an
artificial strategy curated through human knowledge and
intervention which could be biased by the prompt
designers.
- - - - - - - - - - - - - - - - - -
I have been reading about Residual Vector Quantisation
Variational AutoEncoder RQ-VAE.
- https://arxiv.org/pdf/1711.00937
- https://notesbylex.com/residual-vector-quantisation #dailyreport #promptengineering #vae #recsys #emacs

Title: P2: P1: Prompt-engineering CoT [2024-11-20 Wed]
answering shortly. Ex. “Yes. No. Idk”. Models are
highly influenced by the distribution they have been
trained on.
- Model starts to struggle with generating the correct
CoT-paths when the steps become 3 or #dailyreport #promptengineering #vae #recsys #emacs

Title: P1: P1: Prompt-engineering CoT [2024-11-20 Wed]
selecting most probable next word. This give a big
reasoning boost.
- LLMs can reason if we consider the alternative decoding paths.
- Model is predisposed to immediate problem-solving, by #dailyreport #promptengineering #vae #recsys #emacs

Title: P0: Prompt-engineering CoT [2024-11-20 Wed]
I have been reading "Chain-of-Thought Reasoning without
Prompting" https://arxiv.org/pdf/2402.10200

Technique that increase reasoning with costs of LLM
computations by keeps track of multiple potential
sequences at each step, then selects the top ‘k’ most
probable sequences from these new sequences. It is beam
approach than replce "gready decoding" approch by just #dailyreport #promptengineering #vae #recsys #emacs

Title: P5: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
query fully
- big input information, prompt engineering, tables and
code
- user need images and structures, AI need text -
multimodal challenge.
蠡 #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P5: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
query fully
- big input information, prompt engineering, tables and
code
- user need images and structures, AI need text -
multimodal challenge.
蠡 #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P5: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
query fully
- big input information, prompt engineering, tables and
code
- user need images and structures, AI need text -
multimodal challenge.
蠡 #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P5: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
query fully
- big input information, prompt engineering, tables and
code
- user need images and structures, AI need text -
multimodal challenge.
蠡 #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
dissemination of final analysis and trading signal

My thoughts LLM challenges:
- flexible measurement of work required to complete the #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
dissemination of final analysis and trading signal

My thoughts LLM challenges:
- flexible measurement of work required to complete the #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
dissemination of final analysis and trading signal

My thoughts LLM challenges:
- flexible measurement of work required to complete the #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
dissemination of final analysis and trading signal

My thoughts LLM challenges:
- flexible measurement of work required to complete the #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- Sentence similarity: N-gram, Embeddings, ralative position in document penalty.
- T0: Published, T+10min: download, T+30min: Sentiment
analysis, T+55min: domain expert validate and
incorporate results into final analysis, T+60min: #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- Sentence similarity: N-gram, Embeddings, ralative position in document penalty.
- T0: Published, T+10min: download, T+30min: Sentiment
analysis, T+55min: domain expert validate and
incorporate results into final analysis, T+60min: #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- Sentence similarity: N-gram, Embeddings, ralative position in document penalty.
- T0: Published, T+10min: download, T+30min: Sentiment
analysis, T+55min: domain expert validate and
incorporate results into final analysis, T+60min: #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P4: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- Sentence similarity: N-gram, Embeddings, ralative position in document penalty.
- T0: Published, T+10min: download, T+30min: Sentiment
analysis, T+55min: domain expert validate and
incorporate results into final analysis, T+60min: #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
and LLama-Index is poor and their interface &
dependencies are changing frequently

International news sentiment analysis. 20000 news daily.
- Steps: entity recognition, sentiment analysis LM, entity #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P3: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
linking.
- Old, new: find matching sentence pairs, “what is macro
topic of the two sentences?”, “what is the difference
between the sentences in terms of macro variables?”,
Reasining table, “Given {sentence difference} what is
the shift in monetory policy stance. Use {table} as a
guide for reasoning.” -> Looser, NoChange, Tighter. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
and LLama-Index is poor and their interface &
dependencies are changing frequently

International news sentiment analysis. 20000 news daily.
- Steps: entity recognition, sentiment analysis LM, entity #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P3: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
linking.
- Old, new: find matching sentence pairs, “what is macro
topic of the two sentences?”, “what is the difference
between the sentences in terms of macro variables?”,
Reasining table, “Given {sentence difference} what is
the shift in monetory policy stance. Use {table} as a
guide for reasoning.” -> Looser, NoChange, Tighter. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
and LLama-Index is poor and their interface &
dependencies are changing frequently

International news sentiment analysis. 20000 news daily.
- Steps: entity recognition, sentiment analysis LM, entity #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P3: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
linking.
- Old, new: find matching sentence pairs, “what is macro
topic of the two sentences?”, “what is the difference
between the sentences in terms of macro variables?”,
Reasining table, “Given {sentence difference} what is
the shift in monetory policy stance. Use {table} as a
guide for reasoning.” -> Looser, NoChange, Tighter. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
and LLama-Index is poor and their interface &
dependencies are changing frequently

International news sentiment analysis. 20000 news daily.
- Steps: entity recognition, sentiment analysis LM, entity #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P3: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
linking.
- Old, new: find matching sentence pairs, “what is macro
topic of the two sentences?”, “what is the difference
between the sentences in terms of macro variables?”,
Reasining table, “Given {sentence difference} what is
the shift in monetory policy stance. Use {table} as a
guide for reasoning.” -> Looser, NoChange, Tighter. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- challenges:
+ all the frameworks are changing quickly
+ a lot of basic functionality is still missing
+ the code quality of major projects, such as LangChain #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- challenges:
+ all the frameworks are changing quickly
+ a lot of basic functionality is still missing
+ the code quality of major projects, such as LangChain #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- challenges:
+ all the frameworks are changing quickly
+ a lot of basic functionality is still missing
+ the code quality of major projects, such as LangChain #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P2: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- challenges:
+ all the frameworks are changing quickly
+ a lot of basic functionality is still missing
+ the code quality of major projects, such as LangChain #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- The search string is not necessarily the entire
question.
- correct formatting of question is important
- TDD: define the attributes of a good answer as early as
possible #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- The search string is not necessarily the entire
question.
- correct formatting of question is important
- TDD: define the attributes of a good answer as early as
possible #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- The search string is not necessarily the entire
question.
- correct formatting of question is important
- TDD: define the attributes of a good answer as early as
possible #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
- The search string is not necessarily the entire
question.
- correct formatting of question is important
- TDD: define the attributes of a good answer as early as
possible #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
MIRAI and chat developers insights:
- Retain the structure of the document as well as possible
(e.g. headlines)
- Composing a sufficient prompt context is more complex
than posting the retrived results #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
MIRAI and chat developers insights:
- Retain the structure of the document as well as possible
(e.g. headlines)
- Composing a sufficient prompt context is more complex
than posting the retrived results #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
MIRAI and chat developers insights:
- Retain the structure of the document as well as possible
(e.g. headlines)
- Composing a sufficient prompt context is more complex
than posting the retrived results #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P1: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
MIRAI and chat developers insights:
- Retain the structure of the document as well as possible
(e.g. headlines)
- Composing a sufficient prompt context is more complex
than posting the retrived results #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
branches will be: AD, streaming videos, robotics, video
games, batteries, vehicles, space.

MIRAI: AI Research assistent architecture.
- RAG (Azure AI Search) on papers with tags. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
branches will be: AD, streaming videos, robotics, video
games, batteries, vehicles, space.

MIRAI: AI Research assistent architecture.
- RAG (Azure AI Search) on papers with tags. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
branches will be: AD, streaming videos, robotics, video
games, batteries, vehicles, space.

MIRAI: AI Research assistent architecture.
- RAG (Azure AI Search) on papers with tags. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P2: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
branches will be: AD, streaming videos, robotics, video
games, batteries, vehicles, space.

MIRAI: AI Research assistent architecture.
- RAG (Azure AI Search) on papers with tags. #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
*Econimic news*
- USA and Google have most success in model development.
- Miscrosoft and Nvidia have lower costs for models
training.
- Range at atomic energy companies stock prices, next #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
*Econimic news*
- USA and Google have most success in model development.
- Miscrosoft and Nvidia have lower costs for models
training.
- Range at atomic energy companies stock prices, next #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
*Econimic news*
- USA and Google have most success in model development.
- Miscrosoft and Nvidia have lower costs for models
training.
- Range at atomic energy companies stock prices, next #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P1: P0: I have been at Raiffeisen Bank AI Conference. [2024-11-16 Sat]
*Econimic news*
- USA and Google have most success in model development.
- Miscrosoft and Nvidia have lower costs for models
training.
- Range at atomic energy companies stock prices, next #dailyreport #sentiment #chatbot #researchassistent #ai

Title: P3: conference of "Selectel" cloud provider report [2024-10-20 Sun]
instructions, and then translate them into real-world
actions by reversing the terms, such as "computational
resource" -> "water."
蠡 #dailyreport #dataplatform #data #datascience #mlops #cloud

Title: P3: conference of "Selectel" cloud provider report [2024-10-20 Sun]
instructions, and then translate them into real-world
actions by reversing the terms, such as "computational
resource" -> "water."
蠡 #dailyreport #dataplatform #data #datascience #mlops #cloud

Title: P3: conference of "Selectel" cloud provider report [2024-10-20 Sun]
instructions, and then translate them into real-world
actions by reversing the terms, such as "computational
resource" -> "water."
蠡 #dailyreport #dataplatform #data #datascience #mlops #cloud

Title: P3: conference of "Selectel" cloud provider report [2024-10-20 Sun]
instructions, and then translate them into real-world
actions by reversing the terms, such as "computational
resource" -> "water."
蠡 #dailyreport #dataplatform #data #datascience #mlops #cloud