https://modelsatwork.news/article/ibm-research-cuga-harness-appworld-same-model-30-to-81-percent-vendor-published Models at Worken 2026-11-04T00:57:00.000Z IBM Research: same model, harness swing from 30% to 81% on AppWorld Agents, Vendor-published, Agent evaluation, Open source, Governance https://modelsatwork.news/article/aws-edb-postgres-ai-semantic-layer-agentcore-column-comments-grants-vendor-published Models at Worken 2026-11-03T23:55:00.000Z AWS and EDB: Postgres column comments as an agent's data layer Amazon Bedrock AgentCore, Postgres, Vendor-published, Access control, MCP https://modelsatwork.news/article/anthropic-flashprove-open-source-proof-which-model-answered Models at Worken 2026-11-03T23:20:00.000Z Anthropic's FlashProve: proof of which model wrote a response Anthropic, Research, Security, Verification, Open source https://modelsatwork.news/article/finic-kairos-open-source-fraud-decisioning-coding-agent-tunes-it-show-hn Models at Worken 2026-11-03T21:58:00.000Z Finic's Kairos: open-source fraud decisions that a coding agent tunes Open source, Show HN, Agents, Decision models, Self-hosting https://modelsatwork.news/article/aws-bedrock-kimi-k3-india-in-country-inference-ultrahuman-vendor-published Models at Worken 2026-11-03T21:05:00.000Z Amazon Bedrock adds India-only inference for Kimi K3 Amazon Bedrock, Open-weight models, Data residency, Prompt caching, Vendor-published https://modelsatwork.news/article/aws-cartesia-sonic-voice-agents-sagemaker-ec2-deployment-vendor-published Models at Worken 2026-11-03T20:20:00.000Z AWS and Cartesia: running a 90 ms voice model inside your own VPC Vendor-published, Amazon SageMaker AI, Inference, Self-hosting, Voice agents https://modelsatwork.news/article/aws-agentcore-gateway-on-behalf-of-token-exchange-servicenow-entra-vendor-published Models at Worken 2026-11-03T19:05:00.000Z AWS: keep the user's identity when an agent calls ServiceNow Amazon Bedrock AgentCore, Access control, Agent security, Vendor-published, Agents https://modelsatwork.news/article/gen-digital-norton-revamp-agentcore-web-search-news-engine-vendor-published Models at Worken 2026-11-03T17:05:00.000Z Gen Digital: Norton Revamp's news engine on AgentCore Web Search Amazon Bedrock AgentCore, Case study, Vendor-published, Coding agents, Productivity https://modelsatwork.news/article/cio-com-seven-ways-ai-budgets-blow-out-agent-loops-frontier-model-routing-cost-per-pr Models at Worken 2026-11-03T14:58:00.000Z CIO.com: seven ways AI budgets blow out, from agent loops to frontier defaults Cost governance, Agent cost, Token cost, Model selection, Routing https://modelsatwork.news/article/nvidia-auto-ontology-open-source-context-layer-agents-text-to-sql-hacker-news Models at Worken 2026-11-03T14:40:00.000Z NVIDIA open-sources Auto Ontology, a context layer for data agents NVIDIA, Open source, Agents, Data quality, Show HN https://modelsatwork.news/article/anthropic-message-threads-35-percent-lower-time-to-first-token-500k-1m-tokens-claude-code-default Models at Worken 2026-11-03T13:05:00.000Z Anthropic: message threads cut median time to first token about 35% Anthropic, Claude, API, Context management, Agents, Cost https://modelsatwork.news/article/activtrak-heavy-ai-users-work-up-to-90-minutes-longer-9140-workers-cio-reports Models at Worken 2026-11-03T12:10:00.000Z ActivTrak: heavy AI users work up to 90 minutes longer a day, CIO reports Adoption, Surveys, Change management, Productivity https://modelsatwork.news/article/anthropic-claude-api-message-threads-beta-send-only-new-messages-5-minute-expiry Models at Worken 2026-11-03T10:00:00.000Z Anthropic's Claude API adds server-side message threads in beta Anthropic, Claude, API, Context management, Agents, Cost https://modelsatwork.news/article/aws-crawl4ai-bedrock-knowledge-bases-web-content-preparation-metadata-filters-vendor-published Models at Worken 2026-11-03T01:57:00.000Z AWS: prepare web pages with Crawl4AI before Bedrock Knowledge Bases Amazon Bedrock, RAG, Enterprise search, Data quality, Vendor-published https://modelsatwork.news/article/anthropic-s-1-says-it-may-imminently-hit-rsp-accelerated-ai-progress-threshold Models at Worken 2026-11-02T22:55:00.000Z Anthropic's S-1/A: it may 'imminently' meet its own AI-R&D threshold Anthropic, Governance, AI R&D, Self-improvement, Human oversight https://modelsatwork.news/article/aws-multi-agent-part-substitution-assistant-deterministic-scoring-vendor-published Models at Worken 2026-11-02T22:05:00.000Z AWS: parts-substitution agent keeps pass/fail verdicts in plain code Amazon Bedrock AgentCore, Multi-agent, Human in the loop, Routing, RAG, Vendor-published https://modelsatwork.news/article/goldman-sachs-restricts-claude-code-github-copilot-to-engineers-bloomberg-via-the-decoder Models at Worken 2026-11-02T21:30:00.000Z Goldman Sachs limits AI coding tools to engineers, Bloomberg reports Coding agents, Access control, Banking, Change management, Governance https://modelsatwork.news/article/arxiv-pretraining-poisoning-agent-backdoor-0-1-percent-92-percent-attack-success Models at Worken 2026-11-02T20:58:00.000Z Paper: poisoning 0.1% of pretraining data plants an agent backdoor Research, Agent security, Security, Open-weight models, Coding agents https://modelsatwork.news/article/anthropic-s-1-internal-claude-use-list-prices-exceeds-personnel-expense-250-fold-90-percent-code Models at Worken 2026-11-02T19:05:00.000Z Anthropic's filing: internal Claude use, at list price, passed payroll Anthropic, Claude, Token cost, Coding agents, Cost governance https://modelsatwork.news/article/aws-sagemaker-seqkd-4b-student-matches-glm-5-3-teacher-shoppingbench-54-percent-vendor-published Models at Worken 2026-11-02T18:15:00.000Z AWS: a distilled 4B agent matches its GLM-5.3 teacher on ShoppingBench Amazon SageMaker AI, Agent cost, Inference, Model selection, Vendor-published https://modelsatwork.news/article/circle-k-incident-triage-agent-bedrock-agentcore-45-60-minutes-to-under-15-vendor-published Models at Worken 2026-11-02T17:30:00.000Z Circle K's triage agent cuts incident response to under 15 minutes Amazon Bedrock AgentCore, Amazon Bedrock, Agents, Human in the loop, Vendor case study https://modelsatwork.news/article/white-house-eo-14434-super-intelligence-term-census-btos-ai-adoption-survey-wording Models at Worken 2026-11-02T15:05:00.000Z EO 14434 swaps 'AI' for 'Super Intelligence' in US federal documents Regulation, Governance, Compliance, Adoption, Surveys https://modelsatwork.news/article/anthropic-gsa-40-percent-discount-claude-government-agencies Models at Worken 2026-11-02T11:58:00.000Z Anthropic: 40% GSA discount on Claude, now for state and local too Pricing, Procurement, Anthropic, Claude, Claude Code https://modelsatwork.news/briefing/2026-11-03 Models at Worken 2026-11-03T13:10:00.000Z The briefing, 2026-11-03: Goldman Sachs reportedly limits AI coding tools to engineers, ending months of use by traders and bankers https://modelsatwork.news/briefing/2026-11-02 Models at Worken 2026-11-02T13:15:00.000Z The briefing, 2026-11-02: NVIDIA says Shopify's tuned open model beat a frontier model on one Sidekick task at 90% lower cost https://modelsatwork.news/briefing/2026-11-02 Models at Worken 2026-11-02T11:30:00.000Z The briefing, 2026-11-02: NVIDIA says Shopify's tuned open model beat a frontier model on one task at 90% lower serving cost https://modelsatwork.news/briefing/2026-11-03 Models at Worken 2026-11-03T11:30:00.000Z The briefing, 2026-11-03: Anthropic's S-1 says its own Claude use, at list price, passed monthly payroll in April https://modelsatwork.news/briefing/2026-11-04 Models at Worken 2026-11-04T11:30:00.000Z The briefing, 2026-11-04: IBM says changing only the agent harness moved one model from 30% to 81% of tasks