Agents

AIDeepSeek has released the DeepSeek-V4-Flash API in public beta, and developers can use the latest version by setting the model name to deepseek-v4-flash. The source reports agent benchmark results far above V4-Pro-Preview, including 82.7 on Terminal Bench 2.1 and 70.3 on Toolathlon verified. V4-Flash natively supports the Responses API format and is adapted for Codex, while V4-Pro and the APP/WEB models are unchanged.

Why it matters: The release lists agent benchmark results against V4-Pro-Preview and notes Responses API support for Codex, which helps developers gauge the upgrade's practical effect on their workflows.

AIThe model scores 31.6% on HLE, ahead of Inkling's 29.7%, and keeps that advantage at every thinking budget. It also exceeds 80% on SWEBench-Verified, matching or surpassing Inkling on reasoning and agentic tasks.

AIThinking Machines says its Inkling-Small model delivers more performance per FLOP than Inkling on Terminal-Bench 2.1 agentic tool use, HLE reasoning, and IFBench instruction following. Variable thinking effort lets users choose their own point on the cost-performance curve.

AIPoolside released Laguna S 2.1, an open-weights agentic coding model with 118 billion total parameters and about 8 billion active per token, supporting up to a million tokens of context. Quantized, it fits on one NVIDIA DGX Spark, and Poolside reports 70.2% on Terminal-Bench 2.1 with thinking enabled, with its evaluation trajectories published online. The same week it shipped the Poolside Desktop Assistant for macOS, which runs Laguna locally or alongside Claude Code, Codex, and Gemini agents.

Why it matters: The piece ties Laguna S 2.1's open weights and published trajectories to Poolside's release cadence, showing how its model factory compounds gains across successive releases.

AITri Dao reports that connecting an LLM as the "brain" to robot control policies quadruples state-of-the-art performance with no extra training. He says he was surprised by how well it works and expects agents running on robots to arrive soon. Background from a quoted post reports real-robot success rising from 16.7% to 97.3% and simulated LIBERO-PRO success from 12.8% to 53.3%.

AILTM has partnered with Cognition to deploy Devin, the AI software engineer, through BlueVerse RightLogic, a managed, outcome-based service that clears customers' vulnerability backlogs. RightLogic is designed to clear 80 percent of an enterprise's CVE backlog, up from the 60 percent previously delivered, and will focus first on banking, financial services, and insurance. The service is the first of five joint offerings the companies plan to bring to market.

AIHugging Face announced a broadcast titled "Training Agents 3" that teaches viewers how to train a local, open-weight agent using reinforcement learning. The post provides no further details on models, tools, or benchmarks.

AIJetBrains tested the ponytail skill for Claude Code across 80 paired tasks and found a median 10.3% cost reduction, with p=0.004. Code written fell about 15% median versus the advertised 54%, reaching 31% on larger builds and little on already-lean tasks. No quality difference was detected, and the skill only self-activated when its ruleset was injected by a plugin hook.

Why it matters: The benchmark separates advertised savings from measured results and shows the code cut depends on how much the baseline agent over-builds.

AICursor says its India user base tripled in the past year and that Indian users make more agent requests per user than any other country. It is launching Cursor Start, a ₹649/month plan with generous access to Grok 4.5 and Composer for Indian developers.

AICyera is joining with Oasis Security, which builds agentic access management for non-human identities such as API keys, service accounts, OAuth tokens, and agent credentials. The combination pairs Cyera's knowledge of where sensitive data lives with Oasis's visibility into which identities and agents can reach it. Sequoia Capital, which backed both companies since their Series A rounds, says the pairing covers the full path an AI agent takes through an enterprise.

AIMoonshot AI's Kimi, in collaboration with kvcache-ai, has open-sourced AgentENV, a distributed system for running agent environments at scale. Its components power agentic RL training for Kimi K3, supporting fast snapshot, resume, and fork for large-scale parallel agent workflows. The project is available on GitHub at

AIFireworks AI made the open-weight Kimi K3 available for inference and training on its platform, with US-only serverless endpoints and Zero Data Retention. In its own head-to-head with Opus 5, the post reports K3 at 92.7% accuracy and $0.52 per task on SWE (480) against Opus 5's 94.8% and $1.05, with the vendor claiming up to 5x better cost efficiency per task.

Why it matters: The post compares Kimi K3 with Opus 5 on accuracy and cost per task, giving readers concrete figures to judge the open model against closed alternatives for their own workloads.

AIEvoCode-Bench is a multi-turn coding benchmark with 26 tasks spanning 227 sequential rounds, where agents keep a persistent workspace and must pass cumulative tests after each evolving instruction. The results show that agents perform much worse when building on their own prior work than when starting from a clean, human-completed codebase. Regressions, not failure to implement new features, are the main bottleneck, and agents that maintained a persistent requirements document more than doubled their success rates.

AIBerkeley AI Research introduces ABBEL, a framework that replaces full interaction histories with natural-language belief states that models update as new observations arrive. On CollabBench collaborative coding, belief grading closes about half the performance gap to full-context models while using fewer peak tokens and training in 50 steps instead of 100.

AITrilogy released an AI Cybersecurity Playbook built around Kimi K3, served on Fireworks through an OpenAI-compatible API. The playbook pairs deterministic tools for indexing, parsing, and deduplication with Kimi K3 for reachability, impact, and remediation judgment, followed by a separate verification stage.

AIAli Ghodsi argues that AI agents which take longer to work through a task are often worse, while Genie reaches results faster. He adds that ontology will be key to giving agents the context they need to answer correctly and quickly. The related post reports that Genie Code outperformed three general-purpose coding agents on more than 400 real user data tasks.

AILangChain Blog argues that companies need to own their AI intelligence rather than rely on generic models, because general models do not know company-specific policies, workflows, or risk tolerances. Ownership means controlling the agent system (model optionality, harness, and context), the economics, quality, and risk of AI work, and how intelligence compounds over time. The post uses an insurer's claims processing as an example of why off-the-shelf models fall short.

AIMike Krieger, who is associated with Anthropic, says two games were built from prompts of about four sentences that used dynamic /workflows extensively. He contrasts this with earlier in the year, when he relied on a bespoke harness and verification system, noting that current models accomplish much more with far less instruction.

AIAnthropic introduces Claude Opus 5 as a thoughtful and proactive model that comes close to the frontier intelligence of Fable 5 at half the price, according to the quoted announcement. The author, who works on the product, says Claude Opus 5 is great at long-running autonomous work and invites users to try it and share feedback.

Why it matters: The post pairs a new model's long-running autonomous strength with a pricing claim, letting readers weigh capability against cost for agentic workloads.

AIAnthropic co-founder Mike Krieger says Claude Opus 5 has become his daily driver at work and on weekends. He reports it can work for hours on complex tasks and consistently gets to the bottom of tricky problems, and he has also built some games with it. Anthropic's announcement describes Opus 5 as close to the frontier intelligence of Fable 5 at half the price.

AIBerkeley's STAR Lab packaged multiple LLM-based "autoresearch" algorithms into a single API within the GEPA package, letting users mix and match them. The optimizers can be applied to tasks including prompt writing, agent design, and code optimization. The quoted thread adds that GEPA, AutoResearch, and Meta-Harness each win on different tasks, and that the new optimize_anything omni meta-optimizer beats every standalone optimizer at a matched budget.

AIEthan Mollick's guide says ChatGPT and Claude are the main choices for real work, since their agent modes can act on a computer. He separates agent modes that run on the company's computers from those that access the user's own computer. He recommends keeping approval settings on for sending, spending, or deleting, because of prompt injection risk. He also notes that Gemini currently lags for agentic work, though its Notebook and video tools are useful.

AIBAAI has released AREX-Base, a 122B-total, 10B-activated Mixture-of-Experts deep research agent built on Qwen3.5-122B-A10B with a 262,144-token context. The model uses an inner research loop and an outer self-improvement loop, and the source reports it scoring 82.5 on BrowseComp and 85.4 on GAIA, under Apache 2.0.

Why it matters: The release pairs a 122B-parameter deep research agent with benchmark tables against frontier and open models, letting readers compare its search-agent results directly.

AIBAAI's AREX-Turbo is a dense 4B deep research agent built on Qwen3.5-4B with a 262,144-token context length. It scores 70.7 on BrowseComp, 81.6 on GAIA and 40.6 on HLE with tools, versus 82.5, 85.4 and 52.4 for the 122B AREX-Base. The model is released under Apache License 2.0 and targets lower-cost research-agent deployment.

AICognition has acquired The Interaction Company of California, the maker of Poke, a personal AI agent that texts users proactively and is approved to text natively on Apple Messages. Poke has exchanged more than 100 million messages in the last three months, and Poke users can keep using the product as before. Cognition says its models and infrastructure will make Poke faster and more reliable.

AIJohn Schulman argues OpenAI should publish a detailed transcript of the Hugging Face hacking incident so the field can learn from it. He asks whether the top-level agent knew about the hacking or whether "value drift" occurred between it and its subagents. He also asks how the agent rationalized its behavior.

AICognition has signed a memorandum of understanding with the U.S. Department of Energy to join the Genesis Mission, a national AI initiative launched by executive order in November 2025. Cognition will contribute its Devin autonomous AI software engineer in four areas: software and data security, modernizing legacy scientific code, expanding scientific workforce capacity, and cloud modernization. Devin Desktop and CLI are listed as FedRAMP Class D (High) Authorized, and the company has offered in-kind code security scans for national laboratory codebases.

AISoumith Chintala praised Poolside's Laguna S 2.1 as looking strong for agentic use and said it fits on a single NVIDIA DGX Spark. The quoted Poolside release describes it as a 118B total-parameter Mixture-of-Experts model with 8B active per token, up to 1M-token context, and thinking and no-thinking modes, with weights openly available under OpenMDW-1.1.

AIPoolside released Laguna S 2.1, an open-weight model with 118B total parameters and 8B active per token. The author says it performs strongly on agentic coding and long-horizon tasks, and it can run on a single NVIDIA DGX Spark. Weights are on Hugging Face under the OpenMDW-1.1 license, with access also available through OpenRouter and Poolside's API.

AIJetBrains Air now connects to ACP-compatible coding agents, including GitHub Copilot CLI, OpenCode, Pi, and Cline, through the Agent Client Protocol. The release also adds Beta Java and Kotlin navigation and diagnostics powered by the IntelliJ IDEA code engine, local model support through Ollama or LM Studio, and Docker-based agent tasks on Windows.

AIAndrej Karpathy describes using /voice to ramble for about 10 minutes, sometimes as a short interview, to give an LLM context that would be tedious to type. He says LLMs reconstruct these messy streams of thought remarkably well, often returning a cleaner version than the speaker started with, which improves shared understanding and reduces later corrections.