mindgitrwx
@mindgitrwx
I use this twitter account as an index table
You might like
We need more papers like this one which examines how AI agents & humans work together Current agents were fast, but not strong enough to do tasks on their own & approached problems from too much of a programing mindset. But combining human & AI resulted in gains in performance
Can AI invent new math? A new paper from DeepMind and renowned mathematician Terence Tao shows how. Using AlphaEvolve, the team merges LLM-generated ideas with automated evaluation to propose, test, and refine mathematical algorithms. In tests on 67 problems across analysis,…
🔥 Anthropic just solved AI’s biggest bottleneck Every agent today burns tokens like fuel every tool call, every definition, every intermediate result jammed into context. Now Anthropic’s introducing the fix: code execution with MCP. Instead of calling tools directly, agents…
BREAKING: Perplexity’s first research paper broke a major limit in LLM scaling NVIDIA and AWS are excited about it. No one’s reported this yet. What I found most useful: → Enables trillion-parameter serving on AWS (previously not feasible) → Faster than DeepSeek’s DeepEP, a…
Want to understand B-trees better? Try btree.app and bplustree.app. These are standalone sandboxes of the visuals I built for my "B-trees and database indexes" article. Helpful for learning B-tree insertion, search, and node splits.
This guy literally shows how Anthropic built a multi-agent AI that researches like a human
🚨 RIP prompt engineering. This new Stanford paper just made it irrelevant with a single technique. It's called Verbalized Sampling and it proves aligned AI models aren't broken we've just been prompting them wrong this whole time. Here's the problem: Post-training alignment…
🚨 MIT just humiliated every major AI lab and nobody’s talking about it. They built a new benchmark called WorldTest to see if AI actually understands the world… and the results are brutal. Even the biggest models Claude, Gemini 2.5 Pro, OpenAI o3 got crushed by humans.…
🔥 GPT-6 may not just be smarter. It literally might be alive (in the computational sense). A new research paper, SEAL: Self-Adapting Language Models (arXiv:2506.10943), describes how an AI can continuously learn after deployment, evolving its own internal representations…
The new 1 Trillion parameter Kimi K2 Thinking model runs well on 2 M3 Ultras in its native format - no loss in quality! The model was quantization aware trained (qat) at int4. Here it generated ~3500 tokens at 15 toks/sec using pipeline-parallelism in mlx-lm:
🚀 Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here. 🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%) 🔹 Executes up to 200 – 300 sequential tool calls without human interference 🔹 Excels in reasoning, agentic search, and coding 🔹 256K context window Built…
AI가 ‘생각한다’는 논거 - 대규모 언어 모델(LLM) 이 단순한 단어 예측을 넘어 실제 이해와 사고의 형태를 보인다는 논의가 확산되고 있음 - 신경과학자 도리스 차오(Doris Tsao) 는 머신러닝이 지난 100년간의 신경과학보다 지능의 본질을 더 많이 밝혀냈다고 평… news.hada.io/topic?id=24142
Mapping LLMs with Sparse Autoencoders pair.withgoogle.com/explorables/sa… An interactive introduction to Sparse Autoencoders and their use cases with Nada Hussein, @shivamravalxai, Jimbo Wilson, Ari Alberich, @NeelNanda5, @iislucas, and @Nithum
who needs a mouse when you can just turn your head 🙂↔️ head orientation drives the act of reading: turn = change article tilt = scroll text
This video nails the biggest misunderstanding in AI coding: The context window isn’t memory. It’s a whiteboard. Cram it with junk, and the model forgets what’s important. Save this one.
possibly a top paper of the year... "first hybrid linear-attention model to beat O(n²) full attention — up to 6.3x faster 1M-token decoding with higher accuracy" according to the paper: – wins across short context, long context, and RL tests – up to 6.3x faster decoding at 1m…
I totally stole this and converted it into a Claude Skill. I have already stopped using browser MCPs before, but did not find a good replacement. This one does not look completely terrible. x.com/badlogicgames/…
New blog post, wherein I beat a dead horse for the last time. mariozechner.at/posts/2025-11-…
Holy shit… Google just rewired how AI agents talk to the world 🤯 They’ve built a real-time, bidirectional streaming architecture meaning agents no longer wait for your input to finish before responding. They see, hear, and act while you’re still speaking. They can be…
Can LLMs introspect? Who knows! As an experiment, I recorded my first time reading @Jack_W_Lindsey's great paper on this and give a live review as I go TLDR: I see simple explanations for most things, but models detecting injected thoughts seems maybe like real introspection
New Anthropic research: Signs of introspection in LLMs. Can language models recognize their own internal thoughts? Or do they just make up plausible answers when asked about them? We found evidence for genuine—though limited—introspective capabilities in Claude.
United States Trends
- 1. Jonathan Taylor 20.3K posts
- 2. Bills 112K posts
- 3. Falcons 31.1K posts
- 4. Colts 51.9K posts
- 5. Dolphins 19.5K posts
- 6. Diggs 6,519 posts
- 7. Browns 22.9K posts
- 8. Kyle Williams 5,172 posts
- 9. Daniel Jones 9,971 posts
- 10. Joe Brady 1,716 posts
- 11. Jaxson Dart 3,596 posts
- 12. Penix 10.9K posts
- 13. Parker Washington 2,722 posts
- 14. Dillon Gabriel 1,435 posts
- 15. #Bears 3,215 posts
- 16. Drake Maye 6,522 posts
- 17. Justin Fields 1,629 posts
- 18. Liverpool 223K posts
- 19. Starks 2,024 posts
- 20. Max B 25.5K posts
Something went wrong.
Something went wrong.