I have a theory: the amount of information provided in the context differs significantly for these two types of agent scaffolds.
And this causes the reasoning model like o1 to perform differently.
Reasoning models are trained to THINK hard, e.g., by solving extremely…
A brief aside: O1 Pro discussions on immortality are flawed. Even with advanced medical technology, humans can't achieve immortality due to accidents like car crashes or drowning, making it hard to live beyond 2,000 years. Therefore, O1 Pro's thinking is insufficient.
A brief aside: O1 Pro discussions on immortality are flawed. Even with advanced medical technology, humans can't achieve immortality due to accidents like car crashes or drowning, making it hard to live beyond 2,000 years. Therefore, O1 Pro's thinking is insufficient.
From an investor's perspective, I believe it's capital that changes the world, not any particular great individual.
I've always had faith in Sam, and I believe he is a key figure. I've been continuously validating my views.
I believe OpenAI will be great again.
Seeing these AI pioneers and finding they're all crypto folks - quite the pressure!
At least in crypto we're not competing with Wall Street veterans or centuries-old European nobility - no old money advantage here.
Coding 2024: Pick up your mic 🎤 and start chanting your prompts 🎵
The power of your enchanting determines whether you'll conjure epic magic or just a tiny spark ✨
Introducing the Model Context Protocol (MCP)
An open standard we've been working on at Anthropic that solves a core challenge with LLM apps - connecting them to your data.
No more building custom integrations for every data source. MCP provides one protocol to connect them all:
It's off to the races on agentic AI, to keep track of the latest on @windsurf_ai and @codeiumdev you can view our changelog at codeium.com/changelog
Many exciting things in the pipe, excited to see how this space heats up
🤔 Had some political fact-checking lately. Noticed ChatGPT tends to dodge facts, while Claude stays more neutral.
🤖 I once built AI to spot human propaganda. Now ironically, I need another tool to check AI statements - to avoid AI brainwashing! 😅
🤔 Had some political fact-checking lately. Noticed ChatGPT tends to dodge facts, while Claude stays more neutral.
🤖 I once built AI to spot human propaganda. Now ironically, I need another tool to check AI statements - to avoid AI brainwashing! 😅
Many providers offer inference APIs for the same models: for example, there were over nine Llama-3 8B APIs in Summer 2024. Do all of these APIs serve the same completion distribution as the original model?
In our new paper, ✨Model Equality Testing: Which Model is This API…
Every time I learn more about ML & ai, it’s so simple and stupid
Like how did transformers take so long to figure out? Honestly no clue wtf the entire field was doing for 50 years. I see why the old guard is malding
After GraphRAG now the kid on the block is StructRAG!
Imagine asking your AI assistant a complex question that requires piecing together information from multiple sources.
1. StructRAG first identifies the best way to structure the knowledge for the specific task, such as a…
In early 2023, we decided to make Continue open source because we believed
1. the tools used to code with LLMs would be critical infrastructure
2. an ecosystem was key to supporting all developer workflows
3. this would only work if developers worked together
a few core philosophies/opinions behind the design:
- agents should build itself
- functions should be small and use each other (more reliable to reuse stuff)
- store code as graph structure in DB
- build the simplest thing that can build itself
@abdibrokhim This post is one of the things I'm most proud of that received least attention. There are some beautiful ideas in the design and implementation of bitcoin. I should have done a video format of the post, I think it would have gotten ~100X+ more engagement. Maybe still possible.
19K Followers 478 FollowingTeaching & building AI apps → https://t.co/4MQ9vOmIOt
→ Newsletter: https://t.co/3KKVcffvCf
→ My AI Prompts: https://t.co/6KdZMINT79
32K Followers 28K FollowingDaily forecast: stock forecast, indexes, commodities and currencies based on #AI predictive algorithm. Google us: ״I Know First stock forecast״
195 Followers 196 FollowingTechnical Founder of https://t.co/4cHHD2Jqfx. PhD (CS, NLP and Knowledge Graph Embeddings). MLE for 8+ years. Most interested in decision making under uncertainty
98 Followers 595 FollowingDon't make promise when you're in joy.Don't reply when you're sad.Don'take decisions when you're angry.别在喜悦时许诺,别在忧伤时回答,别在愤怒时做决定
36K Followers 5K FollowingExperienced Data Science Leader | PhD in Machine Learning | 4x Author | Black Belt 🥋 in Time Series | Chief Conformal Prediction Promoter| Mathematician |
569 Followers 2 Following$4.25 The Fed just dropped rates to 4.25% and we're going to the moon!
4.25 We Bullish Presented by @MrSolmoon
TG: https://t.co/0qU8WWnyaO
141K Followers 1 FollowingClaude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8dz3D or download the app.
139K Followers 45K FollowingEx @Streamlit @Snowflake Maestro 🪄 • X about AI agents, LLMs, web apps, Python & SEO • My ❤️ is open source • DM for collabs 📩
58K Followers 2K FollowingHead of Design @Cursor_ai. Early @NotionHQ, @Stripe, built startups. I make a world where anyone can make software. Aspiring k-pop idol.
112K Followers 3 FollowingThe official newsroom for @OpenAI. Tweets are on the record.
If you like this account, you’ll love our blog: https://t.co/nEYf8Iq3C0
6K Followers 5K FollowingAI is good & bad, actually.
Tweeting about AI/ML methods, software dev, research, tech and society, social impact.
20yrs in tech, 10 in ML/AI, PhD in comp sci
9K Followers 555 FollowingCreator of XGo (https://t.co/i0rVuQXRRO) and LLGo. Our vision is to enable everyone to become a builder of the world. Qiniu Limited CEO.
136K Followers 1K FollowingPrompt Engineer, dedicated to learning and disseminating knowledge about AI, software engineering, and engineering management.
943 Followers 4 FollowingOfficial AG2 (https://t.co/r1OcgVVcMI) X account!
- Follow AG2 on Github: https://t.co/LRlARataV9
- Join the community on Discord: https://t.co/E9z0UiBeGK