RSI Tracker updateshttps://rsitracker.org/Source-backed evidence updates. Event dates and tracker changes are distinguished.Corrected DGM model attribution: Claude 3.5 Sonnet (New) handles self-modification and SWE-bench evaluation; o3-mini handles Polyglot evaluation. Reported scores are unchanged.https://rsitracker.org/#activitycorrect-dgm-model-attributionSat, 26 Sep 2026 00:00:00 GMTcorrected resultIndexed: Claude Opus 5.5 System Cardhttps://rsitracker.org/research/opus55-card/indexed-opus55-cardTue, 22 Sep 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: Measurements for understanding the pace of AI development inside frontier labshttps://rsitracker.org/research/automation-measurements/indexed-automation-measurementsThu, 17 Sep 2026 00:00:00 GMTnewly indexed historical evidenceAdded the source-attributed B0–L5 framework and historical domain assessment.https://rsitracker.org/research/last-ai-built-by-humans/update-autonomy-frameworkThu, 10 Sep 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: GPT-6 Astra System Cardhttps://rsitracker.org/research/astra-card/indexed-astra-cardThu, 03 Sep 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvementhttps://rsitracker.org/research/ai4ai-paper/indexed-ai4ai-paperThu, 20 Aug 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: Gemini 3.7 Flash Frontier Safety Framework Reporthttps://rsitracker.org/research/gemini37-report/indexed-gemini37-reportnewly indexed historical evidenceIndexed: We are Changing our Developer Productivity Experiment Designhttps://rsitracker.org/research/productivity-redesign/indexed-productivity-redesignTue, 24 Feb 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: Time Horizon 1.1https://rsitracker.org/research/time-horizon-revision/indexed-time-horizon-revisionThu, 29 Jan 2026 00:00:00 GMTnewly indexed historical evidenceIndexed: Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivityhttps://rsitracker.org/research/productivity-trial/indexed-productivity-trialThu, 10 Jul 2025 00:00:00 GMTnewly indexed historical evidenceIndexed: Recent Frontier Models Are Reward Hackinghttps://rsitracker.org/research/reward-hacking/indexed-reward-hackingThu, 05 Jun 2025 00:00:00 GMTnewly indexed historical evidenceIndexed: Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agentshttps://rsitracker.org/research/dgm-paper/indexed-dgm-paperThu, 29 May 2025 00:00:00 GMTnewly indexed historical evidenceIndexed: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithmshttps://rsitracker.org/research/alphaevolve-report/indexed-alphaevolve-reportWed, 14 May 2025 00:00:00 GMTnewly indexed historical evidenceIndexed: PaperBench: Evaluating AI’s Ability to Replicate AI Researchhttps://rsitracker.org/research/paperbench-paper/indexed-paperbench-paperWed, 02 Apr 2025 00:00:00 GMTnewly indexed historical evidenceIndexed: Evaluating frontier AI R&D capabilities of language model agents against human expertshttps://rsitracker.org/research/rebench-report/indexed-rebench-reportFri, 22 Nov 2024 00:00:00 GMTnewly indexed historical evidenceIndexed: MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineeringhttps://rsitracker.org/research/mle-paper/indexed-mle-paperWed, 09 Oct 2024 00:00:00 GMTnewly indexed historical evidence