Skip to content
#Agent

#Agent

Oct 8

TodayOct 8Thu223 items
  1. OpenRouterAI score24

    Our 5-person sales team was drowning before we built Rasp, an AI sales agent using OpenRouter's Ori. Every inbound lead gets researched, many hear back in under 60 seconds, and we save ~600 hours/month. Cost: ~$30/day and getting cheaper by the week. https://openrouter.ai/blog/case-studies/how-an-ai-sales-agent-saved-our-sales-team-600-hours-a-month

    Our 5-person sales team was drowning before we built Rasp, an AI sales agent using OpenRouter's Ori. Every inbound lead gets researched, many hear back in under 60 seconds, and we save ~600 hours/month. Cost: ~$30/day and getting cheaper by the week. https://openrouter.ai/blog/case-studies/how-an-ai-sales-agent-saved-our-sales-team-600-hours-a-month

  2. The Verge · AIAI score30

    SpaceXAI Backs Omarchy Linux Distro With $1.5 Million in Grok Tokens

    SpaceXAI is joining the Omacom Foundation, which oversees the Omarchy Linux distribution, as a Founding Corporate Patron and donating $1.5 million worth of Grok tokens to the project. According to David Heinemeier Hansson's blog post, the tokens will primarily accelerate development, review code, and patch bugs. The partnership follows earlier controversy over Hansson's anti-immigration posts, which have drawn criticism of Omarchy's corporate contributors, including 1Password and Cloudflare.

  4. Artificial IgnoranceAI score52

    Charlie Guo maps the core primitives that make AI agents work over time

    The author argues that agent systems are converging on shared primitives grouped into doing the work, continuing the work, and delegating the work. These include instructions and skills, tools and connectors, sandboxes, sessions, compaction, schedules, and subagents. He also flags memory, proactivity, and agent identity as emerging areas still lacking settled standards.

  5. Epoch AIAI score14

    For example, GPT-6 Astra ran an experiment exploring why AI agents fail to learn with practice. It set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.

    For example, GPT-6 Astra ran an experiment exploring why AI agents fail to learn with practice. It set AI agents’ token budgets too low. Instead of treating this as a mistake, it reported “sensitivity to the acquisition budget” as a key finding.

  6. SiliconANGLE · AIAI score30

    Liquid AI Builds On-Device Personal AI Around Device-Level Context

    Liquid AI is building personal AI that runs on devices such as phones, wearables, PCs, and cars, using its Liquid Context layer, which is optimized for Snapdragon processors, to sit between models, agents, and hardware. The company's agent harness uses its own models to decide which user context to retain and how to compress it within fixed compute limits. Liquid AI is also collaborating with Mercedes-Benz Group AG to bring on-device AI to its cars and plans observability and continuous improvement loops for self-improving agents.

  7. The Verge · AIAI score62

    Anthropic updates Claude usage policy to ban abusive treatment and expand misuse rules

    Anthropic is revising its usage policy for the first time in over a year, adding bans on sustained abusive or cruel behavior toward Claude and on deceptive election and propaganda campaigns. The update also expands weapons restrictions, tightens surveillance bans, and requires a qualified operator able to stop equipment when Claude controls autonomous physical hardware. Terminating conversations remains the primary enforcement mechanism, and the company did not say whether user bans would follow.

  8. Tessl BlogAI score44

    Continuous AI Brings Agentic Automation to Repository Workflows

    Tessl's blog post argues that repository automation needs Continuous AI, a third pillar alongside CI and CD for scheduled, auditable AI workflows that improve repositories over time. The article describes GitHub Agentic Workflows, which harden agentic workflow specifications into GitHub Actions that can run coding agents such as Claude Code, Copilot CLI, Gemini CLI, or Codex-style agents. It emphasizes read-only agent steps, restricted outputs, and human review of pull requests.

  9. Elvis SaraviaAI score46

    RSIGym gives research agents services, lifting SWE-bench Verified to 50.33%

    RSIGym provides a research agent with training, inference, evals, and sandboxes as callable services, so it spends its budget on experiments rather than rebuilding infrastructure. With Opus 5 as the researcher, the improved system rose from 17.67% to 50.33% on SWE-bench Verified. The post also highlights a way to measure co-evolution between harnesses and models.

  10. OdysseyAI score38

    Odyssey-3 is a foundation world model, enabling many applications in physical AI, human experiences, and even how we train intelligences. We're particularly excited by agents learning from experience inside Odyssey-3, working to accomplish objectives.

    Odyssey-3 is a foundation world model, enabling many applications in physical AI, human experiences, and even how we train intelligences. We're particularly excited by agents learning from experience inside Odyssey-3, working to accomplish objectives.

  13. Daniel HanAI score38

    We added OS level sandoxing in Unsloth with bwrap (Linux), seatbelt (Mac) and Windows MXC in Unsloth! Latency per tool call for all is under 100ms. Our software style sandboxing with regex ast checks is 3ms latency as well. Thanks to Windows for collabing with us on MXC!

    We added OS level sandoxing in Unsloth with bwrap (Linux), seatbelt (Mac) and Windows MXC in Unsloth! Latency per tool call for all is under 100ms. Our software style sandboxing with regex ast checks is 3ms latency as well. Thanks to Windows for collabing with us on MXC!

  14. Google ResearchAI score14

    Missed yesterday's demo on adaptive agent environments? Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.

    Missed yesterday's demo on adaptive agent environments? Stop by the #COLM2026 Google booth #107 today at 11:00 AM PT to catch Zifeng Wang presenting EnvHarness — a flexible framework enabling co-evolution between LLM agents and their training environments.

  15. Lauren TanAI score20

    hi @bot look out for interesting things people are doing with Grok Bot on X and slack me a daily digest at 9am. if there’s anything relevant, pick the coolest ideas and suggest how I can use it to improve my workflow

    hi @bot look out for interesting things people are doing with Grok Bot on X and slack me a daily digest at 9am. if there’s anything relevant, pick the coolest ideas and suggest how I can use it to improve my workflow

  17. AWS Machine Learning BlogAI score27

    Share SageMaker HyperPod GPU clusters across teams with isolation and fair scheduling

    AWS published a reference architecture for running multiple teams on one Amazon SageMaker HyperPod EKS cluster, with each team isolated in its own Kubernetes namespace. The design combines AWS IAM Identity Center for authentication, per-team SageMaker AI domains, HyperPod Task Governance for fair resource allocation, and namespace-level cost allocation for per-team spend visibility.

  18. MarkTechPostAI score58

    JetBrains releases Mellum2.1, a 12B MoE open model for coding agents

    JetBrains has released Mellum2.1, a 12B mixture-of-experts thinking model with 2.5B active parameters, under Apache 2.0 on Hugging Face. Post-training reinforcement learning in real software repositories raised SWE-bench Verified from 2.0 to 47.0, according to JetBrains' self-reported results. Qwen3.5-9B still leads on SWE-bench Pro, GPQA Diamond and AIME, and GGUF builds start at 7.0 GB for local use.

  19. Elvis SaraviaAI score22

    Interface ring lets users control AI agents by voice from hand

    Natura AI's Interface is a ring that lets users press and hold to speak requests to AI agents such as Claude Code, Codex, or Hermes, then release to send them. The post argues that screenless interfaces may define the next phase of agent use, since handing work to agents is currently slowed by pulling out a phone. Early-adopter pricing is $99, with shipping slated for January.

  20. Goodfire ResearchAI score57

    Goodfire deploys probe-based cyber monitors on Kimi K3 with a judge cascade

    Goodfire Research describes probe-based cyber monitors for Kimi K3 and GLM 5.3 deployed on a production inference stack. The probe filters suspicious exchanges before an LLM judge reviews them, reaching about 93% recall at a 5.5% benign-session interruption rate at roughly 50x lower judge cost. In FAR.AI's red-teaming, the monitor reduced universal jailbreaks to zero across 140 tested strategies.

  26. Leiphone (雷峰网)AI score62

    Claude Haiku 5.5 gains on computer use but still trails Sonnet 5.5 in terminal coding

    Anthropic released Claude Haiku 5.5, raising its OSWorld 2.1 score from 15.7% to 72.4% and supporting a 1 million token context window. The article notes Haiku 5.5 still scores 39.2% on Terminal-Bench 4.0 against Sonnet 5.5's 70.6%, and that prompts above 100,000 tokens are priced higher, so migration costs need to be measured on real workloads.

  27. Elvis SaraviaAI score33

    We need to rethink security for AI attackers. Security tools were built to stop human attackers. A human might give up on a route after a few hops, but an agent swarm keeps going. Cogent Attack Path Analysis uses @cogent_security's own cyber models to find those longer routes into a company. Then it tells the team which single fix closes each one.

    We need to rethink security for AI attackers. Security tools were built to stop human attackers. A human might give up on a route after a few hops, but an agent swarm keeps going. Cogent Attack Path Analysis uses @cogent_security's own cyber models to find those longer routes into a company. Then it tells the team which single fix closes each one.

  28. Simon WillisonAI score47

    New open source cross-platform (Windows, macOS, Linux) sandboxing library from Microsoft - looks very promising, uses processcontainer/bubblewrap/seatbelt under the hood https://github.com/microsoft/mxc

    New open source cross-platform (Windows, macOS, Linux) sandboxing library from Microsoft - looks very promising, uses processcontainer/bubblewrap/seatbelt under the hood https://github.com/microsoft/mxc

  29. Satya NadellaAI score38

    Satya Nadella proposes Copilot as an OS for work and an infinite SaaS factory

    Satya Nadella outlines Microsoft's vision of Copilot as a new operating system for work spanning every model and task, backed by a governed "headless" business layer. Microsoft announced over 30 new Copilot skills across Dynamics 365 Sales, Service and Customer Insights, plus Microsoft Copilot Managed Runtime for hosting code inside a company's IT-governed environment. Nadella describes this as an "infinite SaaS factory" where users can describe needs and build customizations connected to existing systems of record.

  30. Augment Code BlogAI score62

    Augment Code sells Cosmos, Auggie CLI, and Context Engine assets to Harness

    Augment Code is selling select assets, including Cosmos, Auggie CLI, and the Code Context Engine, to Harness, and the product team is moving to Harness. The company says Harness's integrated platform delivers these capabilities to customers more effectively than building them independently. Harness describes itself as building the Autonomous SDLC Platform for shipping AI-written code across enterprises.

    AIWhy it matters: The announcement shows how a coding AI company is folding its products into a larger software delivery platform, a shift that shapes how enterprise teams will buy these tools.

  31. SantiagoAI score22

    We are always talking about the dark side of AI and how bad people will use it to exploit vulnerabilities everywhere. But there's always an antidote. These guys built a platform that uses agents to protect your systems from attacks: • It builds a map of your potential vulnerabilities • It looks for ways an attacker could find a path to your sensitive data • It recommends changes to protect your system

    We are always talking about the dark side of AI and how bad people will use it to exploit vulnerabilities everywhere. But there's always an antidote. These guys built a platform that uses agents to protect your systems from attacks: • It builds a map of your potential vulnerabilities • It looks for ways an attacker could find a path to your sensitive data • It recommends changes to protect your system

  33. Karl's AI Watts (卡尔的AI沃茨)AI score16

    Author rewrites GoodCase case clustering and storage allocation using Opus 5.5

    The author says GoodCase's case clustering, similar-case recommendations, mobile layout, and multi-country web acceleration, including how storage is split across Vercel, Cloudflare, and Supabase, were all rewritten with Opus 5.5. The post also notes Claude's usage quota has held up well for this work, with a longer write-up planned.

  34. CNBC · TechnologyAI score36

    Amazon Launches Pricier Alexa Tablets and Drops Budget Fire Lineup

    Amazon unveiled 8-inch, 11-inch and 12-inch Alexa tablets priced from $230 to $550 and said it is ditching its budget Fire lineup. The devices run Android rather than Fire OS, and preorders open Thursday with shipping starting Oct. 14. Amazon said it will support the Fire lineup for four years after the final shipment but is no longer manufacturing new units.

  36. ZDNet · AIAI score36

    Only 10% of IT chiefs use agentic AI for legacy modernization, Kyndryl finds

    A Kyndryl survey of 2,000 senior IT decision-makers found only 10% are applying agentic AI as a modernization tool, and nearly half report being behind schedule with cost overruns. Researchers say agentic AI shows early promise for mapping hidden dependencies, generating code, and creating documentation, while Andy Thurai, a former IBM chief strategist, warns that AI-driven infrastructure sprawl could make compute costs unpredictable.

  37. Tessl BlogAI score52

    Enterprise AI agents need governed memory, not larger retrieval stores

    The author argues that agents working across a company fail because they lack the decisions and context recorded in threads, meetings, and DMs, not because the model is weak. The approach stores distilled claims with source evidence and time, never overwrites facts, labels missing information explicitly, and resolves permissions before the model runs. The report cites results on LongMemEval, including 99.8% top-ten evidence recall and $8.24 ingestion cost, and says an open-weight model can match frontier extraction quality.

  39. The Verge · AIAI score58

    Google launches a universal Gemini agent for enterprise work tasks

    Google is launching a "universal" Gemini agent that works across apps and devices in the background, available in private preview to enterprise customers. Users can chat with it and assign tasks from the Gemini Enterprise app, and it works inside Gmail, Drive, Docs, Sheets, and Calendar as well as third-party apps like Slack and Microsoft 365. The source notes it runs in the cloud, keeps the same context across devices, and can use job-specific sub-agents.

  40. Nous ResearchAI score31

    Advancing our mission to deliver ubiquitous powerful agents to everyone, Hermes Agent is on the new ASUS ProArt RTX Spark PCs: MuseTree and ComfyUI integrations plus local model support on up to 128 GB of unified memory. A complete creative stack that runs on your own machine.

    Advancing our mission to deliver ubiquitous powerful agents to everyone, Hermes Agent is on the new ASUS ProArt RTX Spark PCs: MuseTree and ComfyUI integrations plus local model support on up to 128 GB of unified memory. A complete creative stack that runs on your own machine.