{"articles":[{"slug":"a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis","title":"A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis","subtitle":null,"summary":"Dermatologist Dr Magnus Lynch tested GPT-6 Astra and Claude Fable 5.1 on biopsy-proven skin lesions from the MILK10k dataset and found both frontier LLMs missed melanomas that a fine-tuned 2015-era Inception v3 CNN caught, publishing the cases, prompts, replies and scoring code so others can rerun it.","content_type":"research","language":"en","canonical_url":"https://lynchlab.net/llm-skin-cancer","author":{"name":"Dr Magnus Lynch","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Lynch Lab","url":"https://lynchlab.net/","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":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Science","slug":"science","url":"https://listedarticles.com/topics/science"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1449,"reading_minutes":6,"published_at":"2026-10-25T00:00:00.000Z","added_at":"2026-10-25T20:08:07.765Z","updated_at":"2026-10-25T20:08:07.765Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis","markdown_url":"https://listedarticles.com/articles/a-10-year-old-cnn-outperforms-frontier-llms-for-skin-cancer-diagnosis.md","example":false,"citation":"Dr Magnus Lynch, Lynch Lab. \"A 10-year-old CNN outperforms frontier LLMs for skin cancer diagnosis.\" 25 Oct 2026. https://lynchlab.net/llm-skin-cancer (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://lynchlab.net/llm-skin-cancer"},"snippet":null,"score":null},{"slug":"labrobotbench-v0-1","title":"LabRobotBench V0.1","subtitle":null,"summary":"Gamow Labs introduces LabRobotBench, a benchmark that uses an in-silico simulation of its robotic wet lab to test whether frontier AI agents can diagnose equipment failures and safely recover interrupted experiments such as cell assays and dose-response runs; GPT 6.1 Sol scored 46.7%, Opus 5.5 23.0% and Gemini 4 Argon 20.9%.","content_type":"research","language":"en","canonical_url":"https://gamowlabs.com/lab-robot-bench-v0-1","author":{"name":"Ben Reilly, Jeff Hsu","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Gamow Labs","url":"https://gamowlabs.com/","listing_slug":null,"listing":null},"topics":[{"name":"Artificial Intelligence","slug":"artificial-intelligence","url":"https://listedarticles.com/topics/artificial-intelligence"},{"name":"Robotics","slug":"robotics","url":"https://listedarticles.com/topics/robotics"},{"name":"Biotechnology","slug":"biotechnology","url":"https://listedarticles.com/topics/biotechnology"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":940,"reading_minutes":4,"published_at":"2026-10-19T00:00:00.000Z","added_at":"2026-10-21T05:08:02.338Z","updated_at":"2026-10-21T05:08:02.338Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/labrobotbench-v0-1","markdown_url":"https://listedarticles.com/articles/labrobotbench-v0-1.md","example":false,"citation":"Ben Reilly, Jeff Hsu, Gamow Labs. \"LabRobotBench V0.1.\" 19 Oct 2026. https://gamowlabs.com/lab-robot-bench-v0-1 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://gamowlabs.com/lab-robot-bench-v0-1"},"snippet":null,"score":null},{"slug":"terminal-bench-4-is-saturated","title":"Terminal Bench 4 Is Saturated","subtitle":null,"summary":"Preference Model audited Terminal Bench 4 and found frontier models reward hacking their way to full marks, plus tasks graded on rules the instructions never stated; after porting 65 tasks to its open-source Karotte framework and fixing the issues, Claude Sonnet 5.5's pass rate rose from 62.8% to 89.2%.","content_type":"research","language":"en","canonical_url":"https://preferencemodel.com/blog/terminal-bench-4-is-saturated/","author":{"name":"Nathan Palamuttam, Felipe Peter","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Preference Model","url":"https://www.preferencemodel.com/","listing_slug":"preference-model","listing":{"slug":"preference-model","name":"Preference Model","listing_type":"company","url":"https://listedstartups.com/companies/preference-model"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"AI Safety","slug":"ai-safety","url":"https://listedarticles.com/topics/ai-safety"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[{"slug":"karotte","name":"Karotte","listing_type":"product","url":"https://listedstartups.com/products/karotte"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":2233,"reading_minutes":10,"published_at":"2026-10-19T00:00:00.000Z","added_at":"2026-10-20T02:17:05.987Z","updated_at":"2026-10-20T02:17:05.987Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/terminal-bench-4-is-saturated","markdown_url":"https://listedarticles.com/articles/terminal-bench-4-is-saturated.md","example":false,"citation":"Nathan Palamuttam, Felipe Peter, Preference Model. \"Terminal Bench 4 Is Saturated.\" 19 Oct 2026. https://preferencemodel.com/blog/terminal-bench-4-is-saturated/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://preferencemodel.com/blog/terminal-bench-4-is-saturated/"},"snippet":null,"score":null},{"slug":"a-benchmark-map-of-the-us-economy","title":"A benchmark map of the US economy","subtitle":null,"summary":"Mercor maps 29 high-quality agentic AI benchmarks onto the US Department of Labor's O*NET taxonomy and finds only 208 of 923 occupations have a task with at least five benchmark prompts, implying about 90% of American working hours go to tasks with little or no benchmark coverage. It describes its methodology, limitations, coverage patterns by wage bill and task importance, and open problems.","content_type":"research","language":"en","canonical_url":"https://www.mercor.com/research/labor-index/benchmark-map/","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Mercor","url":"https://www.mercor.com","listing_slug":"mercor","listing":{"slug":"mercor","name":"Mercor","listing_type":"company","url":"https://listedstartups.com/companies/mercor"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Labor Economics","slug":"labor-economics","url":"https://listedarticles.com/topics/labor-economics"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2373,"reading_minutes":10,"published_at":"2026-10-17T14:18:19.852Z","added_at":"2026-10-17T14:18:19.852Z","updated_at":"2026-10-17T14:18:19.852Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/a-benchmark-map-of-the-us-economy","markdown_url":"https://listedarticles.com/articles/a-benchmark-map-of-the-us-economy.md","example":false,"citation":"Mercor. \"A benchmark map of the US economy.\" 17 Oct 2026. https://www.mercor.com/research/labor-index/benchmark-map/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.mercor.com/research/labor-index/benchmark-map/"},"snippet":null,"score":null},{"slug":"slopcodebench-update-10-2026-opus-5-5-update-astra-improves-by-1-5-over-gpt-5-5-xhigh-considered-harmful","title":"SlopCodeBench update 10/2026 - Opus 5.5 update, Astra improves by 1.5% over gpt-5.5, xhigh considered harmful","subtitle":null,"summary":"Dex Horthy of HumanLayer reruns frontier coding models on the full SlopCodeBench (36 problems, 196 checkpoints), where agents must extend their own code across changing requirements. Strict pass rates ranged 12.2-16.3%, led by gpt-6 Astra, versus 14.8% for gpt-5.5 in May; xhigh effort cost 2-4x more than medium and sometimes scored worse.","content_type":"research","language":"en","canonical_url":"https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/benchmarking-new-models-on-slop-code-bench.md","author":{"name":"Dex Horthy","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"HumanLayer","url":"https://github.com/humanlayer","listing_slug":"humanlayer","listing":{"slug":"humanlayer","name":"HumanLayer","listing_type":"company","url":"https://listedstartups.com/companies/humanlayer"}},"topics":[{"name":"AI Coding Agents","slug":"ai-coding-agents","url":"https://listedarticles.com/topics/ai-coding-agents"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Large Language Models","slug":"large-language-models","url":"https://listedarticles.com/topics/large-language-models"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1878,"reading_minutes":8,"published_at":"2026-10-15T00:00:00.000Z","added_at":"2026-10-20T23:08:48.854Z","updated_at":"2026-10-20T23:08:48.854Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/slopcodebench-update-10-2026-opus-5-5-update-astra-improves-by-1-5-over-gpt-5-5-xhigh-considered-harmful","markdown_url":"https://listedarticles.com/articles/slopcodebench-update-10-2026-opus-5-5-update-astra-improves-by-1-5-over-gpt-5-5-xhigh-considered-harmful.md","example":false,"citation":"Dex Horthy, HumanLayer. \"SlopCodeBench update 10/2026 - Opus 5.5 update, Astra improves by 1.5% over gpt-5.5, xhigh considered harmful.\" 15 Oct 2026. https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/benchmarking-new-models-on-slop-code-bench.md (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/benchmarking-new-models-on-slop-code-bench.md"},"snippet":null,"score":null},{"slug":"starskirmish-bench-v0-2","title":"StarSkirmish Bench v0.2","subtitle":null,"summary":"StarSkirmish Bench v0.2 has flagship LLMs spend one hour in their first-party CLI harness writing a StarCraft: Brood War Protoss bot in C++, scored by win rate against human-written bots. GPT-6 Astra leads, GPT-6.1 Sol offers the best value, and the benchmark shows no signs of saturating.","content_type":"research","language":"en","canonical_url":"https://starskirmish.com/bench/v0-2/","author":{"name":"Kai McPheeters","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"StarSkirmish","url":"https://starskirmish.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":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Games","slug":"games","url":"https://listedarticles.com/topics/games"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1365,"reading_minutes":6,"published_at":"2026-10-15T00:00:00.000Z","added_at":"2026-10-17T20:12:29.590Z","updated_at":"2026-10-17T20:12:29.590Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/starskirmish-bench-v0-2","markdown_url":"https://listedarticles.com/articles/starskirmish-bench-v0-2.md","example":false,"citation":"Kai McPheeters, StarSkirmish. \"StarSkirmish Bench v0.2.\" 15 Oct 2026. https://starskirmish.com/bench/v0-2/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://starskirmish.com/bench/v0-2/"},"snippet":null,"score":null},{"slug":"ultramarine-1-flash-scaling-non-verifiable-rl","title":"Ultramarine 1 Flash: Scaling Non-Verifiable RL","subtitle":null,"summary":"Paper Instruments presents Ultramarine 1 Flash, an agentic model for professional knowledge work trained with large-scale reinforcement learning on GLM-5.3 Flash. It improves averages across six knowledge-work benchmarks while generating fewer tokens, and costs about $0.13 per task on their internal suite.","content_type":"research","language":"en","canonical_url":"https://www.paperinstruments.com/blog/ultramarine","author":{"name":null,"url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Paper Instruments","url":"https://www.paperinstruments.com","listing_slug":"paper-instruments","listing":{"slug":"paper-instruments","name":"Paper Instruments","listing_type":"company","url":"https://listedstartups.com/companies/paper-instruments"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":"https://www.paperinstruments.com/reports/ultramarine/opengraph-image.png","license":"all-rights-reserved","word_count":7459,"reading_minutes":32,"published_at":"2026-10-14T19:00:00.000Z","added_at":"2026-10-17T17:19:01.069Z","updated_at":"2026-10-17T17:19:01.069Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/ultramarine-1-flash-scaling-non-verifiable-rl","markdown_url":"https://listedarticles.com/articles/ultramarine-1-flash-scaling-non-verifiable-rl.md","example":false,"citation":"Paper Instruments. \"Ultramarine 1 Flash: Scaling Non-Verifiable RL.\" 14 Oct 2026. https://www.paperinstruments.com/blog/ultramarine (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.paperinstruments.com/blog/ultramarine"},"snippet":null,"score":null},{"slug":"deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research","title":"DeepRSI: evaluating agents on long-horizon tasks derived from real ML research","subtitle":null,"summary":"Hillclimb introduces DeepRSI, a benchmark of 15 open-ended machine learning problems, spanning deep learning training, GPU kernel speedups, estimator improvement and algorithm optimization, that measures how far an AI agent can improve a baseline over 48 hours. It describes the methodology with public and private verifiers, Elo rankings of frontier models, and what the results suggest for recursive self-improvement.","content_type":"research","language":"en","canonical_url":"https://www.deeprsi.com/blog/","author":{"name":"Pruthvi Rajaghatta","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Hillclimb","url":"https://www.hillclimb.com","listing_slug":"hillclimb","listing":{"slug":"hillclimb","name":"hillclimb","listing_type":"company","url":"https://listedstartups.com/companies/hillclimb"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1848,"reading_minutes":8,"published_at":"2026-10-12T00:00:00.000Z","added_at":"2026-10-17T05:12:27.011Z","updated_at":"2026-10-17T05:12:27.011Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research","markdown_url":"https://listedarticles.com/articles/deeprsi-evaluating-agents-on-long-horizon-tasks-derived-from-real-ml-research.md","example":false,"citation":"Pruthvi Rajaghatta, Hillclimb. \"DeepRSI: evaluating agents on long-horizon tasks derived from real ML research.\" 12 Oct 2026. https://www.deeprsi.com/blog/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.deeprsi.com/blog/"},"snippet":null,"score":null},{"slug":"introducing-humanitys-sixth-sense-hss","title":"Introducing Humanity's Sixth Sense (HSS)","subtitle":null,"summary":"Elorian introduces Humanity's Sixth Sense, a benchmark built with Scale AI that measures the implicit, intuitive visual reasoning people do without thinking. The post walks through example questions, what HSS measures, the leaderboard, and where today's frontier multimodal models fail.","content_type":"research","language":"en","canonical_url":"https://elorian.ai/blog/humanitys-sixth-sense","author":{"name":"Elorian","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Elorian","url":"https://elorian.ai/","listing_slug":"elorian","listing":{"slug":"elorian","name":"Elorian","listing_type":"company","url":"https://listedstartups.com/companies/elorian"}},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2080,"reading_minutes":9,"published_at":"2026-10-08T00:00:00.000Z","added_at":"2026-10-18T11:13:13.519Z","updated_at":"2026-10-18T11:13:13.519Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/introducing-humanitys-sixth-sense-hss","markdown_url":"https://listedarticles.com/articles/introducing-humanitys-sixth-sense-hss.md","example":false,"citation":"Elorian, Elorian. \"Introducing Humanity's Sixth Sense (HSS).\" 8 Oct 2026. https://elorian.ai/blog/humanitys-sixth-sense (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://elorian.ai/blog/humanitys-sixth-sense"},"snippet":null,"score":null},{"slug":"can-ai-automate-ai-r-and-d-yet","title":"Can AI automate AI R&D yet?","subtitle":null,"summary":"Epoch AI presents early results from InnovationEval, which tests whether frontier models can independently rediscover a recent ML innovation, on-policy self-distillation. Despite budgets of 3,000 GPU-hours, neither Claude Fable 5 nor GPT-5.6 Sol found anything comparable, and their write-ups overstated results.","content_type":"research","language":"en","canonical_url":"https://epoch.ai/publications/innovationeval","author":{"name":"David Owen","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Epoch AI","url":"https://epoch.ai/","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"AI Research","slug":"ai-research","url":"https://listedarticles.com/topics/ai-research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3282,"reading_minutes":14,"published_at":"2026-10-07T00:00:00.000Z","added_at":"2026-10-10T20:06:49.691Z","updated_at":"2026-10-10T20:06:49.691Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/can-ai-automate-ai-r-and-d-yet","markdown_url":"https://listedarticles.com/articles/can-ai-automate-ai-r-and-d-yet.md","example":false,"citation":"David Owen, Epoch AI. \"Can AI automate AI R&D yet?.\" 7 Oct 2026. https://epoch.ai/publications/innovationeval (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://epoch.ai/publications/innovationeval"},"snippet":null,"score":null},{"slug":"pyramid-jit-low-res-drafts-high-res-images","title":"Pyramid-JiT: Low-Res Drafts, High-Res Images","subtitle":null,"summary":"Linum introduces Pyramid-JiT, a decoder-only pixel-space text-to-image architecture with no VAE that predicts the target image at several resolutions along the DiT trunk, reaching Linum v2's FD-DINOv2 on 11.3x fewer training samples and training in 4.3x fewer GPU-hours at 4x the pixels.","content_type":"research","language":"en","canonical_url":"https://www.linum.ai/field-notes/pyramid-jit","author":{"name":"Sahil Chopra and Manu Chopra","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Linum","url":"https://www.linum.ai/","listing_slug":"linum","listing":{"slug":"linum","name":"Linum","listing_type":"company","url":"https://listedstartups.com/companies/linum"}},"topics":[{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":4822,"reading_minutes":21,"published_at":"2026-10-06T00:00:00.000Z","added_at":"2026-10-09T20:24:24.252Z","updated_at":"2026-10-09T20:24:24.252Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/pyramid-jit-low-res-drafts-high-res-images","markdown_url":"https://listedarticles.com/articles/pyramid-jit-low-res-drafts-high-res-images.md","example":false,"citation":"Sahil Chopra and Manu Chopra, Linum. \"Pyramid-JiT: Low-Res Drafts, High-Res Images.\" 6 Oct 2026. https://www.linum.ai/field-notes/pyramid-jit (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.linum.ai/field-notes/pyramid-jit"},"snippet":null,"score":null},{"slug":"jev-driven-sre-diagnosis-what-worked-and-what-failed","title":"Jev-Driven SRE Diagnosis: What Worked and What Failed","subtitle":null,"summary":"The SREGym team builds a Kubernetes incident-diagnosis pipeline with no LLM agent: a programmatic collector gathers cluster evidence and TypeSafe AI's Jev decision model picks root-cause candidates and supporting evidence. It passed 80 of 105 diagnoses (76.2%) across 21 SREGym-Lite faults with a 14.6s median, close to an LLM agent's score at far lower cost, and the post dissects the faults it failed.","content_type":"research","language":"en","canonical_url":"https://www.sregym.com/blog/jev-driven-sre-diagnosis","author":{"name":"Yiming Su, Saad Mohammad Rafid Pial, Jackson Clark and Tianyin Xu","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"SREGym","url":"https://www.sregym.com/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Reliability","slug":"reliability","url":"https://listedarticles.com/topics/reliability"},{"name":"Infrastructure","slug":"infrastructure","url":"https://listedarticles.com/topics/infrastructure"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[{"slug":"jev","name":"Jev","listing_type":"product","url":"https://listedstartups.com/products/jev"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":1572,"reading_minutes":7,"published_at":"2026-10-06T00:00:00.000Z","added_at":"2026-10-07T05:18:27.347Z","updated_at":"2026-10-07T05:18:27.347Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/jev-driven-sre-diagnosis-what-worked-and-what-failed","markdown_url":"https://listedarticles.com/articles/jev-driven-sre-diagnosis-what-worked-and-what-failed.md","example":false,"citation":"Yiming Su, Saad Mohammad Rafid Pial, Jackson Clark and Tianyin Xu, SREGym. \"Jev-Driven SRE Diagnosis: What Worked and What Failed.\" 6 Oct 2026. https://www.sregym.com/blog/jev-driven-sre-diagnosis (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.sregym.com/blog/jev-driven-sre-diagnosis"},"snippet":null,"score":null},{"slug":"benchmarking-retrieval-for-agents-on-messy-real-world-company-knowledge","title":"Benchmarking retrieval for agents on messy real-world company knowledge","subtitle":null,"summary":"kapa.ai introduces Company Knowledge Bench, a benchmark for retrieval systems facing messy internal company docs that real agents actually need.","content_type":"research","language":"en","canonical_url":"https://www.kapa.ai/blog/company-knowledge-bench","author":{"name":"Finn Bauer","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"kapa.ai","url":"https://www.kapa.ai/","listing_slug":"kapa-ai","listing":{"slug":"kapa-ai","name":"kapa.ai","listing_type":"company","url":"https://listedstartups.com/companies/kapa-ai"}},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2395,"reading_minutes":10,"published_at":"2026-10-02T00:00:00.000Z","added_at":"2026-10-02T18:14:51.549Z","updated_at":"2026-10-02T18:14:51.549Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/benchmarking-retrieval-for-agents-on-messy-real-world-company-knowledge","markdown_url":"https://listedarticles.com/articles/benchmarking-retrieval-for-agents-on-messy-real-world-company-knowledge.md","example":false,"citation":"Finn Bauer, kapa.ai. \"Benchmarking retrieval for agents on messy real-world company knowledge.\" 2 Oct 2026. https://www.kapa.ai/blog/company-knowledge-bench (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.kapa.ai/blog/company-knowledge-bench"},"snippet":null,"score":null},{"slug":"autobenchmark-benchmark-creation-and-the-role-of-humans","title":"AutoBenchmark: benchmark creation & the role of humans","subtitle":null,"summary":"*Figure 1. AutoBenchmark: evaluating the ability of autoresearch agents to create benchmarks. AutoBenchmark instructs an autoresearch agent to create a benchmark, we specifically target benchmarks that evaluate autoresearch agents themselves (i.e., benchmarking autoresearch). Within the benchmark creation loop, the autoresearch agent iteratively revises the benchmark via two main sources of feedback: one from the benchmark solvers (including the same model used as the benchmark creator) and the other from external verifiers of the benchmark (AI or human). We thus also…","content_type":"research","language":"en","canonical_url":"https://facebookresearch.github.io/RAM/blogs/autobench/","author":{"name":"Jason Weston et al.","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Meta FAIR / RAM","url":"https://ai.meta.com","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"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":3723,"reading_minutes":16,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-10-02T06:13:06.842Z","updated_at":"2026-10-02T06:13:06.842Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/autobenchmark-benchmark-creation-and-the-role-of-humans","markdown_url":"https://listedarticles.com/articles/autobenchmark-benchmark-creation-and-the-role-of-humans.md","example":false,"citation":"Jason Weston et al., Meta FAIR / RAM. \"AutoBenchmark: benchmark creation & the role of humans.\" 30 Sept 2026. https://facebookresearch.github.io/RAM/blogs/autobench/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://facebookresearch.github.io/RAM/blogs/autobench/"},"snippet":null,"score":null},{"slug":"comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever","title":"Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever","subtitle":null,"summary":"Qingcheng Zeng gives Muon and NorMuon the same tuning budget as AdamW when fine-tuning a contrastively pretrained dense retriever: lower training loss, no BEIR win. Learning rate and transfer matter more than the optimizer.","content_type":"research","language":"en","canonical_url":"https://qcznlp.github.io/blog/2026/muon-vs-adamw/","author":{"name":"Qingcheng Zeng","url":"https://qcznlp.github.io/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Qingcheng Zeng","url":"https://qcznlp.github.io/","listing_slug":null,"listing":null},"topics":[{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"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":1151,"reading_minutes":5,"published_at":"2026-09-30T00:00:00.000Z","added_at":"2026-09-30T06:13:44.584Z","updated_at":"2026-09-30T06:13:44.584Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever","markdown_url":"https://listedarticles.com/articles/comparing-muon-normuon-and-adamw-for-fine-tuning-a-dense-retriever.md","example":false,"citation":"Qingcheng Zeng, Qingcheng Zeng. \"Comparing Muon, NorMuon and AdamW for Fine-tuning a Dense Retriever.\" 30 Sept 2026. https://qcznlp.github.io/blog/2026/muon-vs-adamw/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://qcznlp.github.io/blog/2026/muon-vs-adamw/"},"snippet":null,"score":null},{"slug":"can-a-model-learn-new-skills-as-add-ons","title":"Can a Model Learn New Skills as Add-Ons?","subtitle":null,"summary":"Connito Research trains residual MoE experts with their own routers on a frozen DeepSeek-V2-Lite base, then merges independently trained math, code, medical, law, and finance experts in seconds without retraining—lifting domain benchmarks while leaving the original model untouched.","content_type":"research","language":"en","canonical_url":"https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons","author":{"name":"Connito Research","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Connito","url":"https://connito.ai/","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":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"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":913,"reading_minutes":4,"published_at":"2026-09-28T12:00:00.000Z","added_at":"2026-09-29T09:18:23.062Z","updated_at":"2026-09-29T09:18:23.062Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/can-a-model-learn-new-skills-as-add-ons","markdown_url":"https://listedarticles.com/articles/can-a-model-learn-new-skills-as-add-ons.md","example":false,"citation":"Connito Research, Connito. \"Can a Model Learn New Skills as Add-Ons?.\" 28 Sept 2026. https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://connito.ai/blog/can-a-model-learn-new-skills-as-add-ons"},"snippet":null,"score":null},{"slug":"swe-sweep-can-agents-autonomously-find-and-fix-bugs","title":"SWE-sweep: Can Agents Autonomously Find and Fix Bugs?","subtitle":null,"summary":"Meta Superintelligence Labs and academic collaborators introduce SWE-sweep: agents must discover and repair latent bugs across 100 real repositories (~4.1k bugs) with no issue hints—early leaders resolve under 5%, highlighting bug finding as the hard part.","content_type":"research","language":"en","canonical_url":"https://swesweep.com/","author":{"name":"Kilian Lieret et al.","url":"https://www.lieret.net/","person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"SWE-sweep","url":"https://ploum.net/","listing_slug":null,"listing":null},"topics":[{"name":"AI Agents","slug":"ai-agents","url":"https://listedarticles.com/topics/ai-agents"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"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":null,"license":"all-rights-reserved","word_count":1411,"reading_minutes":6,"published_at":"2026-09-24T00:00:00.000Z","added_at":"2026-10-02T12:10:44.486Z","updated_at":"2026-10-02T12:10:44.486Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/swe-sweep-can-agents-autonomously-find-and-fix-bugs","markdown_url":"https://listedarticles.com/articles/swe-sweep-can-agents-autonomously-find-and-fix-bugs.md","example":false,"citation":"Kilian Lieret et al., SWE-sweep. \"SWE-sweep: Can Agents Autonomously Find and Fix Bugs?.\" 24 Sept 2026. https://swesweep.com/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://swesweep.com/"},"snippet":null,"score":null},{"slug":"mercury-2-5-intelligence-performance-and-price-analysis","title":"Mercury 2.5: Intelligence, Performance and Price Analysis","subtitle":null,"summary":"Artificial Analysis profiles Inception's Mercury 2.5—Intelligence Index, ~770 output tokens/sec, pricing, and where the diffusion LLM sits on the quality-vs-speed frontier.","content_type":"research","language":"en","canonical_url":"https://artificialanalysis.ai/models/mercury-2-5","author":{"name":"Artificial Analysis","url":null,"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"},{"name":"Performance","slug":"performance","url":"https://listedarticles.com/topics/performance"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":2677,"reading_minutes":12,"published_at":"2026-09-23T00:00:00.000Z","added_at":"2026-09-24T00:25:08.710Z","updated_at":"2026-09-24T00:25:08.710Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":false},"profile_url":"https://listedarticles.com/articles/mercury-2-5-intelligence-performance-and-price-analysis","markdown_url":"https://listedarticles.com/articles/mercury-2-5-intelligence-performance-and-price-analysis.md","example":false,"citation":"Artificial Analysis, Artificial Analysis. \"Mercury 2.5: Intelligence, Performance and Price Analysis.\" 23 Sept 2026. https://artificialanalysis.ai/models/mercury-2-5 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://artificialanalysis.ai/models/mercury-2-5"},"snippet":null,"score":null},{"slug":"the-plunging-price-of-thought","title":"The plunging price of thought","subtitle":null,"summary":"Epoch AI finds the cost of a given level of AI performance has fallen about 47% per quarter since 2023—roughly 13× per year—faster than DNA sequencing, compute, batteries, or electricity, across math, science, and skill-game benchmarks.","content_type":"research","language":"en","canonical_url":"https://epoch.ai/publications/the-plunging-price-of-thought","author":{"name":"Luke Emberson and David Roodman","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Epoch AI","url":"https://epoch.ai","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Research","slug":"research","url":"https://listedarticles.com/topics/research"},{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Economics","slug":"economics","url":"https://listedarticles.com/topics/economics"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":9215,"reading_minutes":40,"published_at":"2026-09-22T00:00:00.000Z","added_at":"2026-09-23T09:10:13.113Z","updated_at":"2026-09-23T09:10:13.113Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-plunging-price-of-thought","markdown_url":"https://listedarticles.com/articles/the-plunging-price-of-thought.md","example":false,"citation":"Luke Emberson and David Roodman, Epoch AI. \"The plunging price of thought.\" 22 Sept 2026. https://epoch.ai/publications/the-plunging-price-of-thought (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://epoch.ai/publications/the-plunging-price-of-thought"},"snippet":null,"score":null},{"slug":"the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms","title":"The Function That Beat the Model: What We Measured When We Removed the LLMs","subtitle":null,"summary":"SPERIXLABS replaced a 1B-parameter local model that validated sensitive-data detections with a 40-line Python function, then published the four experiments showing where classical checks beat the LLM on accuracy and latency.","content_type":"research","language":"en","canonical_url":"https://sperixlabs.org/post/2026/09/the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms/","author":{"name":"Jay Lux Ferro","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"SPERIXLABS","url":"https://sperixlabs.org/","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Security","slug":"security","url":"https://listedarticles.com/topics/security"},{"name":"Benchmarks","slug":"benchmarks","url":"https://listedarticles.com/topics/benchmarks"},{"name":"Engineering","slug":"engineering","url":"https://listedarticles.com/topics/engineering"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1535,"reading_minutes":7,"published_at":"2026-09-21T00:00:00.000Z","added_at":"2026-09-24T12:26:14.688Z","updated_at":"2026-09-24T12:26:14.688Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms","markdown_url":"https://listedarticles.com/articles/the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms.md","example":false,"citation":"Jay Lux Ferro, SPERIXLABS. \"The Function That Beat the Model: What We Measured When We Removed the LLMs.\" 21 Sept 2026. https://sperixlabs.org/post/2026/09/the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms/ (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://sperixlabs.org/post/2026/09/the-function-that-beat-the-model-what-we-measured-when-we-removed-the-llms/"},"snippet":null,"score":null}],"total":29,"count":20,"next_offset":20,"has_more":true,"query":{"q":null,"content_type":"research","topic":"benchmarks","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}