Linking pages
- Introducing Gemini 1.5, Google's next-generation AI model https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/ 715 comments
- Hello Qwen2 | Qwen https://qwenlm.github.io/blog/qwen2/ 130 comments
- Big Post About Big Context - by Grigory Sapunov - Gonzo ML https://gonzoml.substack.com/p/big-post-about-big-context 19 comments
- Evaluating long context large language models https://www.artfish.ai/p/long-context-llms 4 comments
- Aman's AI Journal • Primers • Overview of Large Language Models https://aman.ai/primers/ai/LLM/ 1 comment
- Interviewing Louis Castricato of Synth Labs and Eleuther AI on RLHF, Gemini Drama, DPO, founding Carper AI, preference data, reward models, and everything in between https://www.interconnects.ai/p/rlhf-interview-1-louis 1 comment
- Can We Prevent LLMs From Hallucinating? - Brett DiDonato https://brettdidonato.substack.com/p/can-we-prevent-llms-from-hallucinating 1 comment
- Cheap RAGs up for grabs: How to cut costs without sacrificing accuracy? | Pathway https://pathway.com/developers/showcases/adaptive-rag/ 1 comment
- GitHub - HammingHQ/bug-in-the-code-stack: A new benchmark for measuring LLM's capability to detect bugs in large codebase. https://github.com/HammingHQ/bug-in-the-code-stack 1 comment
- How to train a Million Context LLM — with Mark Huang of Gradient.ai https://www.latent.space/p/gradient 1 comment
- The Path To Autonomous AI Agents Through Agent-Computer Interfaces (ACI)—Onward To Web 4.0 https://boltzmannsoul.substack.com/p/the-path-to-autonomous-ai-agents 1 comment
- [Google] Gemini: A Family of Highly Capable Multimodal Models https://gonzoml.substack.com/p/google-gemini-a-family-of-highly 0 comments
- GitHub - LeonEricsson/llmcontext: :anger: Pressure testing the context window of open LLMs https://github.com/LeonEricsson/llmcontext 0 comments
- Google's Gemini 1.5 Pro is a new, more efficient AI model https://www.engadget.com/googles-gemini-15-pro-is-a-new-more-efficient-ai-model-181909354.html 0 comments
- Making LLMs worth every penny | Tom Hipwell https://tomhipwell.co/reading/making_llms_worth_every_penny/ 0 comments
- February '24 Roundup | Tom Hipwell https://tomhipwell.co/blog/february_24_roundup/ 0 comments
- Introducing FastLLM: Qdrant’s Revolutionary LLM - Qdrant https://qdrant.tech/blog/fastllm-announcement/ 0 comments
- Why Google's AI wants you to put glue on pizza https://goodcomputer.substack.com/p/why-googles-ai-wants-you-to-put-glue 0 comments
- How well can LLMs see? · Kabir Khandpur https://kabirk.com/wimmelbench 0 comments
- The 2025 AI Engineering Reading List - Latent Space https://www.latent.space/p/2025-papers 0 comments
Linked pages
- Greg Kamradt on X: "Pressure Testing GPT-4-128K With Long Context Recall 128K tokens of context is awesome - but what's performance like? I wanted to find out so I did a “needle in a haystack” analysis Some expected (and unexpected) results Here's what I found: Findings: * GPT-4’s recall… https://t.co/nHMokmfhW5" / X https://twitter.com/GregKamradt/status/1722386725635580292 1 comment