#models

• Fri, Nov 21, 2025. OpenRouter supports embedding models. BGE base seems pareto optimal with 0.5 cents / MTok and a good MTEB ranking. #embeddings #gpu #models

• Wed, Nov 12, 2025. Once a model generates an output, an agentic look tends not to change the fundamental approach and just tweaks it. So, if a solution is directionally wrong, restarting works better than iterating. Agentic Pelican on a Bicycle #automation #future #image-generation #models #optimization #prompt-engineering

• Sat, Nov 8, 2025. OpenRouter supports embedding models using an OpenAI-like API #embeddings #future #models

• Mon, Oct 27, 2025. A nice visual "benchmark" of text-to-image and image editing models. Seadream 4, Gemini 2.5 Flash, and Qwen Image Edit lead. This includes examples like straightening te Tower of Pisa - which only Flux.1 and Seadream 4 do well on; or removing only the brown M&Ms - which only Qwen Image Edit manages to. #ai-art #gpu #image-generation #markdown #models

• Tue, Oct 7, 2025. Build a corporate strategy simulation game. Pick from a set of scenarios / case studies (with financials, etc.) ALlow the user to propose turn-based actions. Use thinking + code to simulate the impact. Let it evolve turn by turn. Compare against multiple players. #future #models

• Wed, Aug 20, 2025. ⭐ Models need environments to learn. So far, we have been providing training data. But an environment to interact with, and learn from by itself, is more powerful. That requires a standard for environments. This is a powerful emerging area. #future #models #learning

• Sun, Aug 10, 2025. Topic modeling can be extended in many ways. # #models
  • Structural Topic Models factor in metadata, like year (numeric) or category or author (categorical).
  • Relational Topic Models factor in undirected graph relationships, e.g. parent documents
  • Graph-Regularized Topic Models factors in arbitrary graph relationships, e.g. weighted, directed
  • Neural (GNN + Topic Model) approaches work better for large graphs, long-range dependencies, etc.

• Wed, Jul 23, 2025. Having LLMs go through engineering drawings, floor plans, etc. and understand them, find problems, etc. is an emerging use case. People are using Veo 3 to convert a floor plan into a 3D walk through too. #future #llm-ops #models

• Fri, Jun 20, 2025. Models.dev is an open source database and API of LLM models #database #future #llm-ops #markdown #models

• Thu, Jun 19, 2025. Logprobs are back on models in Vertex AI. Ref #gpu #models

• Fri, May 23, 2025. ⭐ "Agents are models using tools in a loop." -- Hannah Moran Simon Willison #agents #automation #code-agents #future #models

• Mon, May 12, 2025. ⭐ Model reliability is a huge enabler for performance. As models become more reliable, they can work autonomously for longer and that is another kind of scaling. Vending Bench #automation #future #gpu #models

• Fri, Apr 25, 2025. LemonSlice showcases real-time audio-video models (avatars) that are close enough to real. #future #models #voice-cloning

• Sun, Apr 13, 2025. docker model run can run models. Currently, only on Docker Desktop on Mac Ref #models

• Thu, Mar 20, 2025. Alexander Doria shares an interesting perspective on the app space. Model is the product #models
  • Models are natively absorbing app capability and will become killer systems internalising workflows like Chat, Deep Research, Claude Code, Operator, etc. to wipe out the apps and workflow space. Models will "internalize" tool capabilities
  • Opinionated or focused training will be a lever and model providers will acqui-hire the successful trainers
  • API access from model providers will shrink. Selling tokens is not a viable business model given lowering costs

• Fri, Mar 14, 2025. "SRM"s are Small Reasoning Models - like Small Language Models. Phi-4 and DeepScaleR are SRMs. Gemma 3 is a multi-modal SLM. #models

• Thu, Mar 13, 2025. A mental model to consider is: each chat conversation with an LLM is a person or a personality in itself. A day in the life of a model, where its personality evolves. #future #llm-ops #models

• Sun, Feb 16, 2025. HuggingFace has a "Model tree" against each model that shows the model's ancestors and descendants. For example, as of now, Deepseek R1 has 75 adapters, 154 finetunes, and 23 quantizations. #future #huggingface #models

• Mon, Feb 3, 2025. GitHub models is free for anyone to try. The model catalog us extensive and even includes o3-mini which was launched this week (though in limited preview). #future #github #markdown #models

• Sat, Nov 9, 2024. Workflow for AI video creation: Use Meshcapade (meshcapade.com) to generate body movement of a 3D-rendered character. Pass that video to Runway's video-to-video model to generate any visual. Add music from Suno Ref #future #models

• Mon, Aug 12, 2024. Some interesting multi-modal generation models / tools to explore: #future #gpu #image-generation #models
  • Flux for open-weights image generation
  • Runway Gen 3 for video generation
  • Suno for music generation

• Sat, Aug 10, 2024. Embedding models can be fine-tuned. Example: #embeddings #future #gpu #markdown #models #optimization #todo

• Sun, Jul 14, 2024. Models gently grow in capability. It helps to maintain an impossibility list that steadily gets invalidated. Ref #future #models

• Wed, Mar 27, 2024. Representational engineering lets you control LLM output based on preference on the fly. #future #llm-ops #markdown #models #prompt-engineering

• Wed, Mar 13, 2024. Interesting model garden models #future #models

• Wed, Dec 20, 2023. ⭐ This leaderboard included paid models like GPT4 and Claude and compared them with open models on HUMAN + system benchmarks #chatgpt #gpu #models

• Sun, Dec 17, 2023. llm360 publishes models along with training datasets. #future #llm-ops #models

• Fri, Nov 24, 2023. OpenRouter hosts several models and offers them as APIs! #models

• Mon, Nov 6, 2023. 06 Nov 2023: Multimodal model papers on Huggingface #future #huggingface #models