LLMs have started assigning blame. Asked @claudeai to re-examine a code. First: "Let me read the source carefully myself." Then: "The Explore agent was wrong. Look at line 24."
"Myself" — first person. "The Explore agent" — third person. Both Claude. Same model, same session.
My first computer had 4KB of RAM. 12-bit. Self-modifying code. Floating-point paranoia. Four things I learned then still run in everything I build today.
Technically, 4K Words; the byte wasn’t its unit. But the constraint was the same.
→ https://t.co/zm3SmVrc0l
We quietly rebuilt https://t.co/c7zl2jo80X — the studio behind winkNLP and winkComposer.
2¼ people. No VC. 10M+ downloads.
The tools speak for themselves. Now so does the website.
https://t.co/3ATWYb7aXa
From proprietary roots to co-creating @winkjs_org & #winkNLP, Open Source reshaped how I build: freedom with responsibility, openness as mindset.
Thank you @OpenSourceOrg for featuring my journey this #MaintainerMonth.
👉🏽https://t.co/5NNaJQpI6k
Working with #LLMs is lots of fun! Did you ever try asking the following question to ChatGPT 4o?
LLMs are truly dream machines and their dreams are shaped by prompts!
Read the analysis at https://t.co/02MZ5uERH9
Are you currently hiring for a role that includes using Node.js? Reply with a link to the opening and any relevant context.
If you're not, we'd appreciate a repost for visibility 💚
Google’s new Gemma 2B model is indeed very interesting. This compact AI model shows how tiny models can make a significant impact. With lower computational demands, these models can bring advanced AI to more devices, making technology more accessible and cost-effective. Tiny models like Gemma 2B open up new possibilities in real-time data processing and improved privacy. We are planning to integrate it with #winkComposer.
https://t.co/oBr1KUfaSJ
Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet.
Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation.
The models are available to download now directly from Meta or @huggingface. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including @awscloud, @nvidia, @databricks, @groqinc, @dell, @azure and @googlecloud ready on day one.
More details in the full announcement ➡️ https://t.co/hhJoLm5eLV
Download Llama 3.1 models ➡️ https://t.co/rRjvmxqCTC
With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.
Excited to share that #winkNLP has won the prestigious @nasscom AI Gamechangers award (Challenger)! 🏆 Had an amazing time at the @nasscomAI Confluence 2024, engaging with #GenAI startups and gaining valuable insights from panel discussions and lightning talks.
Remembering Apollo 11, the first manned mission to the moon, and honoring the incredible contributions of Margaret Hamilton, NASA’s first software engineer.
🌕🚀
#Apollo11#NASA#WomenInSTEM#SpaceExploration
https://t.co/W2lrpzNMlU
LLMs are dream machines. We direct their dreams with prompts. The prompts start the dream, and mostly produce useful outcomes.
It's only when the dreams go into factually incorrect territory that we label it a "hallucination". It looks like a bug, but it's just the LLM doing what it always does.
~ Andrej Karpathy
#LLM #AI
🎉 WinkNLP's latest release supports various space characters like Em, En, and Thin spaces!
🔍 Key Benefits:
1️⃣ Analyze diverse texts with greater accuracy, capturing the nuances of different writing styles.
2️⃣ Maintain the integrity of original texts, ensuring precise tokenization.
3️⃣ Enhance text mining, and data retrieval with improved space handling.
Checkout at Github: https://t.co/WJCTP8JW3G
#NLP #WinkNLP #Nodejs #Javascript #AI #TextAnalysis
Here's a fun and thought-provoking question for you:
👉 How many types of space characters do you think you have used so far?
Space characters are more diverse than you might think! There a world of space characters! 🛰️🚀
👋 Take a moment to share your experience.
#NLP