Structured LLM outputs

A practical handbook for developers using LLMs to get structured outputs.

DomBusGateway #addon for #homeassistant that permit to use #dombus modules: #relays #inputs #outputs #sensors #EV #solartracker ...

#!/bin/bash

# disconnect every existing connection

IFS=$'\n' read -r -d '' -a outputs < <( pw-link -o && printf '\0' )
IFS=$'\n' read -r -d '' -a inputs < <( pw-link -i && printf '\0' )

# pw-link -d out in

i=0; while [ $i -lt ${#outputs[@]} ]; do
j=0; while [ $j -lt ${#inputs[@]} ]; do
pw-link -d ${outputs[$i]} ${inputs[$j]} 2> /dev/null
((j++));
done

((i++)); done

I'm thinking about making time-lapse videos of my prints and I'm curious if the Prusa XL Buddy board has outputs or open-collector lines that can be managed with gcode to control a camera remote. 🤔 Has anyone tackled something similar or has insights on this?

#3DPrinting #PrusaXL #TimeLapse #XLBuddy #Board #Outputs

#Design #Approaches
Design for meaningful outcomes · People don’t want outputs; they want outcomes https://ilo.im/157zga

_____
#Business #Customers #ProductDesign #UxDesign #UiDesign #WebDesign #Mindsets #Outcomes #Outputs

The thing about this working from home debate that I don't like is that it is being top down implemented.

Different people have different work-life needs & patterns.

#flexibility is key. Success measured by #outputs.

#WFH #Meta https://mastodon.social/@the_verge/111014123691436367

#Personality #Traits in #LargeLanguageModels. The advent of large language models (#LLMs) has revolutionized #naturallanguageprocessing, enabling the generation of coherent and contextually relevant text. We find that: 1) #personality simulated in the #outputs of some LLMs (under specific prompting configurations) is reliable and valid https://arxiv.org/abs/2307.00184
Personality Traits in Large Language Models

The advent of large language models (LLMs) has revolutionized natural language processing, enabling the generation of coherent and contextually relevant human-like text. As LLMs increasingly powerconversational agents used by the general public world-wide, the synthetic personality traits embedded in these models, by virtue of training on large amounts of human data, is becoming increasingly important. Since personality is a key factor determining the effectiveness of communication, we present a novel and comprehensive psychometrically valid and reliable methodology for administering and validating personality tests on widely-used LLMs, as well as for shaping personality in the generated text of such LLMs. Applying this method to 18 LLMs, we found: 1) personality measurements in the outputs of some LLMs under specific prompting configurations are reliable and valid; 2) evidence of reliability and validity of synthetic LLM personality is stronger for larger and instruction fine-tuned models; and 3) personality in LLM outputs can be shaped along desired dimensions to mimic specific human personality profiles. We discuss the application and ethical implications of the measurement and shaping method, in particular regarding responsible AI.

arXiv.org
What is I enjoy while #coding and #programming : is I see results on my #computer and it returns #outputs. I really like it !

⁃ A nota está linkada num widget do #AppleNotes na home screen, então é moleza abrir e fazer isso. Além de ver todo dia.
⁃ No meu #PKM, tenho um recap de #outputs que trago para a nota de acompanhamento de julho
⁃ Aí tô pensando em replicar isso aqui no #Mastodon. Uma forma de me incentivar E de ser mais ativo na comunidade com #escrita - talvez inspirar mais alguém, sei lá.

#writing

I am experimenting with #aiart and would like to publish here some of my #outputs, do you think I should, or should I create a new mastodon page? I know it is a very #flaming subject and there is so much hate about it..

Any #mastodon #instance you would suggest in such case? Or should I just #CW my posts?

Here, a post where I am talking about it: Click me

Post it here
100%
Post it here, but
0%
New, separate account
0%
(just answers or else)
0%
Poll ended at .
Francesco Yoshi Gobbo :linux: (@[email protected])

Attached: 1 image Having so much fun with #ComfyUI !! :ablobattention: #AIart seems so much easy, in truth, there is so much work behind if you want to obtain that particular look or feeling! With #Comfy, it feels like being inside #Nuke or #Natron, #Blender... basically any #compositing software! And in fact, it actually is! Sure, you might also get lucky with a 'amazing landscape' #promt, but would be totally random :blobaviator: #art #ai #StableDiffusion #Tensorflow #machinelearning #nodeCompositing

Qoto Mastodon