{"articles":[{"slug":"context-management-is-an-underrated-habit","title":"Context management is an underrated habit","subtitle":null,"summary":"How you manage context in a Claude Code session has a direct effect on both your token bill and the quality of what you get back. Do it well and you spend less for better work. An efficient session gives Claude the context it needs to finish the job while removing context that has stopped being useful. That means starting with a lean setup, keeping investigations focused, and deliberately deciding when to continue, compact, or start again. Here are the context management techniques we use on the","content_type":"blog_post","language":"en","canonical_url":"https://ideas.fin.ai/p/context-management-is-an-underrated","author":{"name":"Akshay Katyal","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Fin","url":"https://fin.ai/","listing_slug":"fin","listing":{"slug":"fin","name":"Fin","listing_type":"product","url":"https://listedstartups.com/products/fin"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Productivity","slug":"productivity","url":"https://listedarticles.com/topics/productivity"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1257,"reading_minutes":5,"published_at":"2026-10-01T12:00:00.000Z","added_at":"2026-10-01T15:13:20.860Z","updated_at":"2026-10-01T15:13:20.860Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/context-management-is-an-underrated-habit","markdown_url":"https://listedarticles.com/articles/context-management-is-an-underrated-habit.md","example":false,"citation":"Akshay Katyal, Fin. \"Context management is an underrated habit.\" 1 Oct 2026. https://ideas.fin.ai/p/context-management-is-an-underrated (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://ideas.fin.ai/p/context-management-is-an-underrated"},"snippet":null,"score":null},{"slug":"small-decisions-engineering-a-leading-model","title":"Small Decisions: Engineering a Leading Model","subtitle":null,"summary":"AWS engineer Marc Brooker recounts building and training a small leading model hands-on—what worked, how it performed, and what the exercise taught him about modern model-building.","content_type":"blog_post","language":"en","canonical_url":"https://brooker.co.za/blog/2026/09/28/engineering-system-one.html","author":{"name":"Marc Brooker","url":"https://brooker.co.za/blog/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Marc's Blog","url":"https://brooker.co.za/blog/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2024,"reading_minutes":9,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-28T18:15:18.900Z","updated_at":"2026-09-28T18:15:18.900Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/small-decisions-engineering-a-leading-model","markdown_url":"https://listedarticles.com/articles/small-decisions-engineering-a-leading-model.md","example":false,"citation":"Marc Brooker, Marc's Blog. \"Small Decisions: Engineering a Leading Model.\" 28 Sept 2026. https://brooker.co.za/blog/2026/09/28/engineering-system-one.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://brooker.co.za/blog/2026/09/28/engineering-system-one.html"},"snippet":null,"score":null},{"slug":"token-space-font-compiler","title":"Token-space font compiler","subtitle":null,"summary":"A font compiler that makes every LLM token the same width—why monospace-per-token helps visualize chain-of-thought, plus an interactive preview of fonts built from a font + tokenizer pair.","content_type":"blog_post","language":"en","canonical_url":"https://ampdot.mesh.host/token-space-fonts.html","author":{"name":"ampdot","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"ampdot","url":"https://ampdot.mesh.host","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1527,"reading_minutes":7,"published_at":"2026-09-27T03:09:40.436Z","added_at":"2026-09-27T03:09:40.436Z","updated_at":"2026-09-27T03:09:40.436Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/token-space-font-compiler","markdown_url":"https://listedarticles.com/articles/token-space-font-compiler.md","example":false,"citation":"ampdot, ampdot. \"Token-space font compiler.\" 27 Sept 2026. https://ampdot.mesh.host/token-space-fonts.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://ampdot.mesh.host/token-space-fonts.html"},"snippet":null,"score":null},{"slug":"analyzing-frontier-model-progress-with-my-favourite-game-prince-of-persia-apple-ii-1989","title":"Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia (Apple II, 1989)","subtitle":null,"summary":"Priyan uses Jordan Mechner's Prince of Persia as a living benchmark: asking frontier models to port and reason about the classic Apple II game, and what those runs reveal about coding-agent progress.","content_type":"blog_post","language":"en","canonical_url":"https://blog.priyan.in/2026/09/analyzing-frontier-model-progress-with.html","author":{"name":"Priyan R","url":"https://blog.priyan.in/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Priyan's Blog","url":"https://blog.priyan.in/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1825,"reading_minutes":8,"published_at":"2026-09-26T08:00:00.000Z","added_at":"2026-09-26T21:13:37.692Z","updated_at":"2026-09-26T21:13:37.692Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/analyzing-frontier-model-progress-with-my-favourite-game-prince-of-persia-apple-ii-1989","markdown_url":"https://listedarticles.com/articles/analyzing-frontier-model-progress-with-my-favourite-game-prince-of-persia-apple-ii-1989.md","example":false,"citation":"Priyan R, Priyan's Blog. \"Analyzing Frontier Model Progress with My Favourite Game: Prince of Persia (Apple II, 1989).\" 26 Sept 2026. https://blog.priyan.in/2026/09/analyzing-frontier-model-progress-with.html (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://blog.priyan.in/2026/09/analyzing-frontier-model-progress-with.html"},"snippet":null,"score":null},{"slug":"42x-faster-prompt-lookup-drafting-in-llama-cpp","title":"42x Faster Prompt Lookup Drafting in llama.cpp","subtitle":null,"summary":"Four changes to the n-gram caches of llama.cpp make drafting up to 41.6x faster, load the static cache up to 23.5x faster, and lower peak memory up to 2.65x.","content_type":"blog_post","language":"en","canonical_url":"https://jadidbourbaki.github.io/blog/prompt-lookup-llama-cpp/","author":{"name":"Hayder Tirmazi","url":"https://jadidbourbaki.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Hayder Tirmazi","url":"https://jadidbourbaki.github.io/","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"}],"about_listings":[],"cover_image_url":"https://jadidbourbaki.github.io/blog/prompt-lookup-llama-cpp/preview.png","license":"all-rights-reserved","word_count":2954,"reading_minutes":13,"published_at":"2026-09-26T00:00:00.000Z","added_at":"2026-09-27T21:08:42.541Z","updated_at":"2026-09-27T21:08:42.541Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/42x-faster-prompt-lookup-drafting-in-llama-cpp","markdown_url":"https://listedarticles.com/articles/42x-faster-prompt-lookup-drafting-in-llama-cpp.md","example":false,"citation":"Hayder Tirmazi, Hayder Tirmazi. \"42x Faster Prompt Lookup Drafting in llama.cpp.\" 26 Sept 2026. https://jadidbourbaki.github.io/blog/prompt-lookup-llama-cpp/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://jadidbourbaki.github.io/blog/prompt-lookup-llama-cpp/"},"snippet":null,"score":null},{"slug":"tupi-rebuilding-1554-in-the-browser-with-32-ai-agents","title":"Tupi: rebuilding 1554 in the browser with 32 AI agents","subtitle":null,"summary":"How Ruben Marcus rebuilt a 1554 Tupinambá canoe raid as real-time 3D in the browser with Claude Opus 5.5, three.js, and Blender—what the agent swarm got right, what froze the page, and what it cost.","content_type":"blog_post","language":"en","canonical_url":"https://www.rubenmarcus.dev/blog/rebuilding-1554-in-the-browser","author":{"name":"Ruben Marcus","url":"https://www.rubenmarcus.dev/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Ruben Marcus","url":"https://www.rubenmarcus.dev/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Web Development","slug":"web-development","url":"https://listedarticles.com/topics/web-development"},{"name":"History","slug":"history","url":"https://listedarticles.com/topics/history"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1950,"reading_minutes":8,"published_at":"2026-09-26T00:00:00.000Z","added_at":"2026-09-26T06:11:48.987Z","updated_at":"2026-09-26T06:11:48.987Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/tupi-rebuilding-1554-in-the-browser-with-32-ai-agents","markdown_url":"https://listedarticles.com/articles/tupi-rebuilding-1554-in-the-browser-with-32-ai-agents.md","example":false,"citation":"Ruben Marcus, Ruben Marcus. \"Tupi: rebuilding 1554 in the browser with 32 AI agents.\" 26 Sept 2026. https://www.rubenmarcus.dev/blog/rebuilding-1554-in-the-browser (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.rubenmarcus.dev/blog/rebuilding-1554-in-the-browser"},"snippet":null,"score":null},{"slug":"ai-subagents-orchestration-are-now-reliable","title":"AI Subagents orchestration are now reliable","subtitle":null,"summary":"Rafael explains what changed to make AI subagent orchestration reliable enough for real development workflows, and how he uses task decomposition in practice.","content_type":"blog_post","language":"en","canonical_url":"https://dev.to/rafael_dev/ai-subagents-orchestration-are-now-reliable-2hee","author":{"name":"Rafael","url":"https://dev.to/rafael_dev","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"DEV Community","url":"https://dev.to/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"Programming","slug":"programming","url":"https://listedarticles.com/topics/programming"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1397,"reading_minutes":6,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-26T09:19:29.285Z","updated_at":"2026-09-26T09:19:29.285Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/ai-subagents-orchestration-are-now-reliable","markdown_url":"https://listedarticles.com/articles/ai-subagents-orchestration-are-now-reliable.md","example":false,"citation":"Rafael, DEV Community. \"AI Subagents orchestration are now reliable.\" 25 Sept 2026. https://dev.to/rafael_dev/ai-subagents-orchestration-are-now-reliable-2hee (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://dev.to/rafael_dev/ai-subagents-orchestration-are-now-reliable-2hee"},"snippet":null,"score":null},{"slug":"what-a-task-costs-on-opus-5-5","title":"What a task costs on Opus 5.5","subtitle":null,"summary":"claude.dev puts numbers on why two same-priced models can cost very different amounts: every turn resends the conversation, so retries and harness shape dominate the bill.","content_type":"blog_post","language":"en","canonical_url":"https://claude.dev/blog/what-a-task-costs-on-opus-5-5/","author":{"name":"claude.dev","url":"https://claude.dev/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Anthropic","url":"https://www.anthropic.com/","listing_slug":"anthropic","listing":{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Claude","slug":"claude","url":"https://listedarticles.com/topics/claude"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":5165,"reading_minutes":22,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-26T03:13:11.823Z","updated_at":"2026-09-26T03:13:11.823Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/what-a-task-costs-on-opus-5-5","markdown_url":"https://listedarticles.com/articles/what-a-task-costs-on-opus-5-5.md","example":false,"citation":"claude.dev, Anthropic. \"What a task costs on Opus 5.5.\" 25 Sept 2026. https://claude.dev/blog/what-a-task-costs-on-opus-5-5/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://claude.dev/blog/what-a-task-costs-on-opus-5-5/"},"snippet":null,"score":null},{"slug":"is-metas-muse-secretly-running-an-openai-model","title":"Is Meta’s Muse secretly running an OpenAI model?","subtitle":null,"summary":"Is Meta’s Muse secretly running an OpenAI model? I found a model labeled azure/muse-special while Muse was building my website.","content_type":"blog_post","language":"en","canonical_url":"https://mouse.dev/blog/muse-special/","author":{"name":"mouse","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"mouse.dev","url":"https://mouse.dev","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"OpenAI","slug":"openai","url":"https://listedarticles.com/topics/openai"}],"about_listings":[{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":870,"reading_minutes":4,"published_at":"2026-09-25T12:00:00.000Z","added_at":"2026-09-25T21:17:58.696Z","updated_at":"2026-09-25T21:17:58.696Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/is-metas-muse-secretly-running-an-openai-model","markdown_url":"https://listedarticles.com/articles/is-metas-muse-secretly-running-an-openai-model.md","example":false,"citation":"mouse, mouse.dev. \"Is Meta’s Muse secretly running an OpenAI model?.\" 25 Sept 2026. https://mouse.dev/blog/muse-special/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://mouse.dev/blog/muse-special/"},"snippet":null,"score":null},{"slug":"hitting-a-billion-tokens-per-minute-on-one-gpu-by-combining-a-query-planner-and-an-inference-engine","title":"Hitting a billion tokens per minute on one GPU by combining a query planner and an inference engine","subtitle":null,"summary":"Charles Frye and Shreya on the Modal blog: combining a query planner with an inference engine to push AI-SQL queries past a billion tokens per minute on one GPU—why left-deep joins help KV cache, and how they beat naive vLLM-style serving.","content_type":"blog_post","language":"en","canonical_url":"https://modal.com/blog/quail-billion-tpm","author":{"name":"Charles Frye","url":"https://twitter.com/charles_irl","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Modal","url":"https://modal.com/","listing_slug":"modal","listing":{"slug":"modal","name":"Modal","listing_type":"company","url":"https://listedstartups.com/companies/modal"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"}],"about_listings":[],"cover_image_url":"https://modal.com/docs/social-image.png?title=Hitting+a+billion+tokens+per+minute+on+one+GPU+by+combining+a+query+planner+and+an+inference+engine&socialType=blog","license":"all-rights-reserved","word_count":4181,"reading_minutes":18,"published_at":"2026-09-24T00:00:00.000Z","added_at":"2026-09-27T21:08:30.930Z","updated_at":"2026-09-27T21:08:30.930Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/hitting-a-billion-tokens-per-minute-on-one-gpu-by-combining-a-query-planner-and-an-inference-engine","markdown_url":"https://listedarticles.com/articles/hitting-a-billion-tokens-per-minute-on-one-gpu-by-combining-a-query-planner-and-an-inference-engine.md","example":false,"citation":"Charles Frye, Modal. \"Hitting a billion tokens per minute on one GPU by combining a query planner and an inference engine.\" 24 Sept 2026. https://modal.com/blog/quail-billion-tpm (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://modal.com/blog/quail-billion-tpm"},"snippet":null,"score":null},{"slug":"how-to-serve-trillions-of-tokens-for-trillion-parameter-coding-agents","title":"How to serve trillions of tokens for trillion-parameter coding agents","subtitle":null,"summary":"Modal explains how it serves coding-agent inference at extreme scale—performance and efficiency techniques for trillion-parameter models generating trillions of tokens, written for teams facing the same workload.","content_type":"blog_post","language":"en","canonical_url":"https://modal.com/blog/trillion-tokens-trillion-parameters","author":{"name":"Charles Frye","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Modal","url":"https://modal.com","listing_slug":"modal","listing":{"slug":"modal","name":"Modal","listing_type":"company","url":"https://listedstartups.com/companies/modal"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"}],"about_listings":[],"cover_image_url":"https://modal.com/docs/social-image.png?title=How+to+serve+trillions+of+tokens+for+trillion-parameter+coding+agents&socialType=blog","license":"all-rights-reserved","word_count":6972,"reading_minutes":30,"published_at":"2026-09-23T18:30:00.000Z","added_at":"2026-09-24T03:16:50.575Z","updated_at":"2026-09-24T03:16:50.575Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/how-to-serve-trillions-of-tokens-for-trillion-parameter-coding-agents","markdown_url":"https://listedarticles.com/articles/how-to-serve-trillions-of-tokens-for-trillion-parameter-coding-agents.md","example":false,"citation":"Charles Frye, Modal. \"How to serve trillions of tokens for trillion-parameter coding agents.\" 23 Sept 2026. https://modal.com/blog/trillion-tokens-trillion-parameters (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://modal.com/blog/trillion-tokens-trillion-parameters"},"snippet":null,"score":null},{"slug":"honest-about-uncertainty-i-tried-to-rebuild-jevs-rlcd-from-a-blog-post","title":"Honest About Uncertainty: I Tried to Rebuild Jev’s RLCD From a Blog Post","subtitle":null,"summary":"Anthony Maio reverse-engineers a plausible RLCD training loop for decision-only models from TypeSafe’s Jev blog post, then trains and evaluates a small Qwen3-0.6B checkpoint—with code and ablations.","content_type":"blog_post","language":"en","canonical_url":"https://anthonymaio.substack.com/p/honest-about-uncertainty-i-tried","author":{"name":"Anthony Maio","url":"https://anthonymaio.substack.com","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Anthony Maio","url":"https://anthonymaio.substack.com","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[{"slug":"jev","name":"Jev","listing_type":"product","url":"https://listedstartups.com/products/jev"},{"slug":"typesafe-ai","name":"TypeSafe AI","listing_type":"company","url":"https://listedstartups.com/companies/typesafe-ai"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":4310,"reading_minutes":19,"published_at":"2026-09-23T12:00:00.000Z","added_at":"2026-09-27T06:22:16.316Z","updated_at":"2026-09-27T06:22:16.316Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/honest-about-uncertainty-i-tried-to-rebuild-jevs-rlcd-from-a-blog-post","markdown_url":"https://listedarticles.com/articles/honest-about-uncertainty-i-tried-to-rebuild-jevs-rlcd-from-a-blog-post.md","example":false,"citation":"Anthony Maio, Anthony Maio. \"Honest About Uncertainty: I Tried to Rebuild Jev’s RLCD From a Blog Post.\" 23 Sept 2026. https://anthonymaio.substack.com/p/honest-about-uncertainty-i-tried (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://anthonymaio.substack.com/p/honest-about-uncertainty-i-tried"},"snippet":null,"score":null},{"slug":"why-claude-opus-5-5-still-wont-fix-your-ai-agents","title":"Why Claude Opus 5.5 Still Won't Fix Your AI Agents","subtitle":null,"summary":"VooStack argues that swapping in a stronger LLM won’t fix unreliable agents: the real work is orchestration, observability, and API design—the engineering discipline required to ship agents that hold up.","content_type":"blog_post","language":"en","canonical_url":"https://voostack.com/blogs/why-claude-opus-5-5-wont-fix-ai-agents","author":{"name":"VooStack","url":"https://voostack.com/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"VooStack","url":"https://voostack.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Software Engineering","slug":"software-engineering","url":"https://listedarticles.com/topics/software-engineering"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"Developer Tools","slug":"developer-tools","url":"https://listedarticles.com/topics/developer-tools"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1545,"reading_minutes":7,"published_at":"2026-09-23T00:00:00.000Z","added_at":"2026-09-30T06:14:12.620Z","updated_at":"2026-09-30T06:14:12.620Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/why-claude-opus-5-5-still-wont-fix-your-ai-agents","markdown_url":"https://listedarticles.com/articles/why-claude-opus-5-5-still-wont-fix-your-ai-agents.md","example":false,"citation":"VooStack, VooStack. \"Why Claude Opus 5.5 Still Won't Fix Your AI Agents.\" 23 Sept 2026. https://voostack.com/blogs/why-claude-opus-5-5-wont-fix-ai-agents (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://voostack.com/blogs/why-claude-opus-5-5-wont-fix-ai-agents"},"snippet":null,"score":null},{"slug":"evals-skills-for-coding-agents","title":"Evals Skills for Coding Agents","subtitle":null,"summary":"Hamel Husain publishes evals-skills—agent skills for AI product evaluation covering audit, error analysis, synthetic data, judge prompts, evaluator validation, and RAG evals, distilled from work with dozens of companies.","content_type":"blog_post","language":"en","canonical_url":"https://hamelhusain.substack.com/p/evals-skills-for-coding-agents","author":{"name":"Hamel Husain","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Hamel Husain","url":"https://hamelhusain.substack.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":585,"reading_minutes":3,"published_at":"2026-09-22T21:21:27.264Z","added_at":"2026-09-22T21:21:27.264Z","updated_at":"2026-09-22T21:21:27.264Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/evals-skills-for-coding-agents","markdown_url":"https://listedarticles.com/articles/evals-skills-for-coding-agents.md","example":false,"citation":"Hamel Husain, Hamel Husain. \"Evals Skills for Coding Agents.\" 22 Sept 2026. https://hamelhusain.substack.com/p/evals-skills-for-coding-agents (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://hamelhusain.substack.com/p/evals-skills-for-coding-agents"},"snippet":null,"score":null},{"slug":"tackling-robotics-with-v-lm-agents","title":"Tackling Robotics with (V)LM Agents","subtitle":null,"summary":"Nishanth J. Kumar surveys recent demos and ideas around GPT-6 and other vision-language models solving robotics tasks—summarizing approaches and offering thoughts on what works and what still breaks.","content_type":"blog_post","language":"en","canonical_url":"https://nishanthjkumar.com/blog/2026/Tackling-Robotics-with-(V)LM-Agents/","author":{"name":"Nishanth J. Kumar","url":"https://nishanthjkumar.com","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"nishanthjkumar.com","url":"https://nishanthjkumar.com","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Robotics","slug":"robotics","url":"https://listedarticles.com/topics/robotics"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2304,"reading_minutes":10,"published_at":"2026-09-22T15:00:00.000Z","added_at":"2026-09-24T03:17:12.485Z","updated_at":"2026-09-24T03:17:12.485Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/tackling-robotics-with-v-lm-agents","markdown_url":"https://listedarticles.com/articles/tackling-robotics-with-v-lm-agents.md","example":false,"citation":"Nishanth J. Kumar, nishanthjkumar.com. \"Tackling Robotics with (V)LM Agents.\" 22 Sept 2026. https://nishanthjkumar.com/blog/2026/Tackling-Robotics-with-(V)LM-Agents/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://nishanthjkumar.com/blog/2026/Tackling-Robotics-with-(V)LM-Agents/"},"snippet":null,"score":null},{"slug":"claude-opus-5-5-takes-the-top-spot-on-the-artificial-analysis-intelligence-index","title":"Claude Opus 5.5 takes the top spot on the Artificial Analysis Intelligence Index","subtitle":"A 20% price cut, deeper cache discounts, and leading scores on agentic knowledge-work evals.","summary":"Artificial Analysis’s first look at Claude Opus 5.5: Intelligence Index score of 58 at max effort, parity with GPT-6 Astra on Terminal-Bench 4.0, stronger agentic knowledge-work results, and Anthropic’s $4/$20 pricing with cheaper cache reads.","content_type":"blog_post","language":"en","canonical_url":"https://artificialanalysis.ai/articles/claude-opus-5-5","author":{"name":"Artificial Analysis","url":"https://artificialanalysis.ai/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Artificial Analysis","url":"https://artificialanalysis.ai/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[{"slug":"anthropic","name":"Anthropic","listing_type":"company","url":"https://listedstartups.com/companies/anthropic"},{"slug":"claude","name":"Claude","listing_type":"product","url":"https://listedstartups.com/products/claude"},{"slug":"openai","name":"OpenAI","listing_type":"company","url":"https://listedstartups.com/companies/openai"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":609,"reading_minutes":3,"published_at":"2026-09-22T12:00:00.000Z","added_at":"2026-09-23T03:20:52.987Z","updated_at":"2026-09-23T03:20:52.987Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/claude-opus-5-5-takes-the-top-spot-on-the-artificial-analysis-intelligence-index","markdown_url":"https://listedarticles.com/articles/claude-opus-5-5-takes-the-top-spot-on-the-artificial-analysis-intelligence-index.md","example":false,"citation":"Artificial Analysis, Artificial Analysis. \"Claude Opus 5.5 takes the top spot on the Artificial Analysis Intelligence Index.\" 22 Sept 2026. https://artificialanalysis.ai/articles/claude-opus-5-5 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://artificialanalysis.ai/articles/claude-opus-5-5"},"snippet":null,"score":null},{"slug":"i-asked-metas-muse-for-its-filesystem-and-it-sent-me-6-8-gb","title":"I asked Meta’s Muse for its filesystem and it sent me 6.8 GB","subtitle":null,"summary":"A security researcher asks Meta’s privileged Muse AI assistant to export its runtime filesystem—and receives a 6.8 GB dump that reveals how Muse is wired, what it can reach, and why that matters.","content_type":"blog_post","language":"en","canonical_url":"https://mouse.dev/blog/muse-runtime-export/","author":{"name":"Mouse","url":"https://mouse.dev","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Mouse","url":"https://mouse.dev","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1501,"reading_minutes":7,"published_at":"2026-09-22T12:00:00.000Z","added_at":"2026-09-22T15:49:14.640Z","updated_at":"2026-09-22T15:49:14.640Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/i-asked-metas-muse-for-its-filesystem-and-it-sent-me-6-8-gb","markdown_url":"https://listedarticles.com/articles/i-asked-metas-muse-for-its-filesystem-and-it-sent-me-6-8-gb.md","example":false,"citation":"Mouse, Mouse. \"I asked Meta’s Muse for its filesystem and it sent me 6.8 GB.\" 22 Sept 2026. https://mouse.dev/blog/muse-runtime-export/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://mouse.dev/blog/muse-runtime-export/"},"snippet":null,"score":null},{"slug":"self-hosting-llm-models-for-software-development","title":"Self-hosting LLM models for software development","subtitle":null,"summary":"Kévin Maschtaler on running medium-sized open LLMs on AWS Spot EC2 for day-to-day software work—what stacks, costs, and performance looked like versus a personal Claude subscription.","content_type":"blog_post","language":"en","canonical_url":"https://www.kmaschta.me/blog/2026/09/22/self-hosting-llm-models","author":{"name":"Kévin Maschtaler","url":"https://www.kmaschta.me/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"kmaschta.me","url":"https://www.kmaschta.me/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1719,"reading_minutes":7,"published_at":"2026-09-22T11:00:00.000Z","added_at":"2026-09-22T12:23:38.707Z","updated_at":"2026-09-22T12:23:38.707Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/self-hosting-llm-models-for-software-development","markdown_url":"https://listedarticles.com/articles/self-hosting-llm-models-for-software-development.md","example":false,"citation":"Kévin Maschtaler, kmaschta.me. \"Self-hosting LLM models for software development.\" 22 Sept 2026. https://www.kmaschta.me/blog/2026/09/22/self-hosting-llm-models (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.kmaschta.me/blog/2026/09/22/self-hosting-llm-models"},"snippet":null,"score":null},{"slug":"mimo-v2-6-pro-intelligence-performance-and-price-analysis","title":"MiMo-V2.6-Pro: Intelligence, Performance and Price Analysis","subtitle":"Artificial Analysis benchmark and cost breakdown of Xiaomi’s open-weight flagship.","summary":"Artificial Analysis’s model page for Xiaomi MiMo-V2.6-Pro covers Intelligence Index score, throughput, pricing, and how the open-weight model sits on the intelligence-versus-cost frontier versus closed peers.","content_type":"blog_post","language":"en","canonical_url":"https://artificialanalysis.ai/models/mimo-v2-6-pro","author":{"name":"Artificial Analysis","url":"https://artificialanalysis.ai/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Artificial Analysis","url":"https://artificialanalysis.ai/","listing_slug":null,"listing":null},"topics":[{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Open Source","slug":"open-source","url":"https://listedarticles.com/topics/open-source"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2734,"reading_minutes":12,"published_at":"2026-09-22T09:08:51.926Z","added_at":"2026-09-22T09:08:51.926Z","updated_at":"2026-09-22T09:08:51.926Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/mimo-v2-6-pro-intelligence-performance-and-price-analysis","markdown_url":"https://listedarticles.com/articles/mimo-v2-6-pro-intelligence-performance-and-price-analysis.md","example":false,"citation":"Artificial Analysis, Artificial Analysis. \"MiMo-V2.6-Pro: Intelligence, Performance and Price Analysis.\" 22 Sept 2026. https://artificialanalysis.ai/models/mimo-v2-6-pro (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://artificialanalysis.ai/models/mimo-v2-6-pro"},"snippet":null,"score":null},{"slug":"evolution-of-llm-architecture","title":"Evolution of LLM Architecture","subtitle":null,"summary":"Amit Shekhar walks through how LLM design moved from RNNs to attention, Transformers, scaling laws, Mixture of Experts, and the open problems still ahead.","content_type":"blog_post","language":"en","canonical_url":"https://outcomeschool.com/blog/evolution-of-llm-architecture","author":{"name":"Amit Shekhar","url":"https://outcomeschool.com","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Outcome School","url":"https://outcomeschool.com","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Education","slug":"education","url":"https://listedarticles.com/topics/education"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":5729,"reading_minutes":25,"published_at":"2026-09-21T00:00:00.000Z","added_at":"2026-09-21T06:26:09.970Z","updated_at":"2026-09-21T06:26:09.970Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/evolution-of-llm-architecture","markdown_url":"https://listedarticles.com/articles/evolution-of-llm-architecture.md","example":false,"citation":"Amit Shekhar, Outcome School. \"Evolution of LLM Architecture.\" 21 Sept 2026. https://outcomeschool.com/blog/evolution-of-llm-architecture (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://outcomeschool.com/blog/evolution-of-llm-architecture"},"snippet":null,"score":null}],"total":46,"count":20,"next_offset":20,"has_more":true,"query":{"q":null,"content_type":"blog_post","topic":"llms","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}