AI - AI Dynamics

Debugging Pinecone metadata retrieval and task deduction issues

By

–

27 March 2023 19h05

Yeah, it’s being stored in Pinecone and I’m pulling 5 most relevant – but need to debug pulling out metadata as all it’s getting is the similarity score now (not helpful). That should fix repeating. Also deducing tasks isn’t done by OpenAI yet – so need to fix that.

→ View original post on X — @yitayml

Human raters blindly evaluate AI model outputs

By

@yitayml

–

27 March 2023 18h59

referring to the fact that the human raters don't know where (which model) the outputs come from.

→ Voir le post original sur X — @jessyseonoob

Meta Launches New AI Model Week Start

By

@jessyseonoob

–

27 March 2023 18h59

Voila on demarre la semaine, une nouvelle #AI chez #meta #muavic https://t.co/wzst6PMzJB
— ⚡Jessy SEO formation #IA générative #chatGPT 🦊 (@jessyseonoob) 27 mars 2023

Voila on demarre la semaine, une nouvelle #AI chez #meta #muavic

LangChain Task Execution with Separate OpenAI Calls

By

–

27 March 2023 18h44

Oh yeah, the thought/observation is using @langchain
, which I'm using to execute each tasks. Separate OpenAI call for task creation/reprioritization

User Joins GPT-4 API Waitlist After Seeing Others Access

By

–

27 March 2023 18h40

Yep – I just forgot to add myself to the gpt4 api waitlist until I saw others getting it…

→ View original post on X — @yitayml

Systematic Blind Evaluation Benchmarks for LLMs Urgently Needed

By

@yitayml

–

27 March 2023 18h37

friendly reminder to everyone that there isn't yet a good & proper systematic blind eval/benchmark of LLMs yet, especially those on real world data/use-cases. if i were in academia this is something i'll work on immediately.

→ View original post on X — @aiatmeta

MuAViC Enables Audio-Visual Learning for Superior Speech Translation

By

@aiatmeta

–

27 March 2023 18h32

MuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings.

More ➡️ https://t.co/FUnlg2dUOq pic.twitter.com/X6sGzU8FCW
— AI at Meta (@AIatMeta) 27 mars 2023

MuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings. More https://
bit.ly/3ZNg76h

Boston Dynamics Robot Dog Acquisition Interest

By

–

27 March 2023 18h26

I'll need to get a Boston Dynamics doggo

AI Agent with Search and Action Capabilities Development

By

–

27 March 2023 18h24

Yep, and it's generating questions by researching the task online. Only has search functionality for now, but can take actions w a few lines of code added.