Show HN: Agent Manager – keyboard-first workflow for running many coding agents
Article URL: https://github.com/wainmann/agent-manager Comments URL: https://news.ycombinator.com/item?id=50406983 Points: 3 # Comments: 0
AI NEWS JOURNAL
AI coding
Follow the latest facts and developments on one topic.
Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls
Run Claude Code as a remote agent on Amazon Bedrock AgentCore. Each coding task runs in its own isolated session in your AWS account, every model call goes through Amazon Bedrock, and the result comes back as a GitHub pull request you review and merge.
A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights
arXiv:2611.07103v1 Announce Type: new Abstract: A challenge to Weight Space Learning as it expands from task specific and vision models to Large Language Models (LLMs) is the absence of a well curated and analyzed LLM population. To address this, we train such a model zoo for application to Weight Space Generation by systematically varying the data mixture composition between web text, books, mathematics, coding, and French across populations of 51M, 124M, and 355M parameter GPT-2 Models, each tier with count N = 100. We analyze these populations by cosine similarity, functional diversity, Leave-One-Mixture-Out modeling, and variance decomposition. We show that the zoo contains diverse models whose variation is structured by training mixture composition. We embed the training mixture composition to condition a Flow Matching model of complete pretrained LLM weights in Gram-PCA compressed weight space. By demonstrating zero-shot generalization to held out mixtures, measuring Continuous Ranked Probability Score skill, as well as finding minimal changes in downstream test-set perplexity and general capability benchmark scores, we show that our generator generalizes on the simplex of data mixtures to produce models that perform similarly to those in the zoo ex nihilo. Finally, we produce all source code and artifacts to support the continued expansion of Weight Space Learning and Generation into the LLM domain.
Show HN: Cerea – yet another self-hosted LLM chat front end
Here is Cerea, a self-hostable, open-source (Apache 2.0) chat+agent frontend for LLMs. It works alone with any OpenAI-compatible inference provider, but it's way better when coupled with the model gateway I'm also developing, Pystino (https://github.com/paoloviviani/Pystino).I came to this after struggling to find a hosted chat interface that was truly open source, that I really enjoyed to use, and that was simple enough to be shared and used by family. In particular, I was looking for something that could provide the smooth and integrated user experience of commercial products for the tasks needed by family (e.g., document editing, form filling, notes and knowledge management), but backed by open models hosted wherever I decide.Then it became richer, now supporting: remote coding agents (wrapping Opencode), delegation and coordination between agents, integration between chat/projects and code agents (this one to me is a pain point for Claude, which I use at work), projects, RAG, rich artifacts support, schedules, and more.You can try it yourself, either cloning the full repo and head to Cerea/kit, or just the deploy kit with a script (https://github.com/paoloviviani/Cerea#quick-start).It's just a docker compose with a ./configure script that helps to generate a sensible .env for the specific scenario. It works in the browser and as a PWA on mobile.I hope you'll enjoy, feel free to reach out for questions. Comments URL: https://news.ycombinator.com/item?id=50384502 Points: 1 # Comments: 0
Show HN: Flawless UI/UX – A design skill and inspection CLI for coding agents
Article URL: https://github.com/smokeeaasd/flawless-ui-ux Comments URL: https://news.ycombinator.com/item?id=50381846 Points: 1 # Comments: 0
The Evolution of Agent Harness: From Chains and Graphs to Code-Based Implementation
Click to view the original article>
Meta acquires AI coding startup Conductor, whose app runs several coding agents at once
Meta Platforms Inc. has acquired artificial intelligence coding startup Conductor in a deal first reported today by Axios. Conductor confirmed it’s joining Meta in a post on its website. Terms were not disclosed. Conductor’s software lets a developer run several coding agents at once, each in an isolated copy of the codebase, and then review […] The post Meta acquires AI coding startup Conductor, whose app runs several coding agents at once appeared first on SiliconANGLE.
Show HN: CXAgent – a multi-agent coding workbench for the terminal, in .NET
Article URL: https://nickprotop.github.io/cxagent/ Comments URL: https://news.ycombinator.com/item?id=50368887 Points: 1 # Comments: 0
Show HN: Alternative to Nvidia Auto-Ontology
This repo provides an alternative to the ontology compiling capabilities of NVIDA Auto-Ontology.The main difference is that it builds the ontology from most of your existing data assets (transformation code, dashboards, docs), instead of building it from your warehouse and semantic layer only.It consists in skills and python scripts that ingest the metadata and docs your team already has, and compile them into YAML and Markdown files structured in a file tree that an agent can use as context to query your data.When your existing asset contradict, or reveal a gap in the business context around your data, it writes down questions for you and your team instead of guessing a plausible meaning.It runs locally in any coding agent. Comments URL: https://news.ycombinator.com/item?id=50363667 Points: 1 # Comments: 0
What Is This Memory Useful For? Measuring Task-Conditioned Utility in Long-Term Agent Memory
arXiv:2611.03930v1 Announce Type: new Abstract: A stored experience may answer one future question and offer little help with another. We measure this task-conditioned utility rather than assigning each memory a single importance score. A task-blind writer stores a memory without seeing the later task; a frozen reader then answers that task with and without the memory, using identical filler. A cost ledger records the resources used to form, store and expose the memory. On single-call factual-recall tasks built from LongMemEval-V2 web-agent memories, the same memory helps more when it contains information needed for the answer. Its mean paired reward gain on these answer-bearing task pairs exceeds that on matched-control pairs by $+0.33$ (95% interval $+0.21$ to $+0.46$). The tested task-blind summaries and structured records yield smaller gains than Raw, including at fixed total context; a budget sweep is consistent with retention of answer-bearing content contributing to the difference. The bearing--control contrast remains positive in a new session with randomized memory position and under a second reader, although individual memory--task labels change. Generic retrieval performs above chance but misses most screen-defined answer-bearing memories. The factual-recall gains do not extend to the tested software-engineering and scientific-coding benchmarks, where even raw memories have no measurable effect. We provide a public, versioned Conditional Memory Utility Dataset of paired measurements and costs. The practical takeaway is to evaluate memory compression by the task utility it preserves alongside its costs. Task-conditioned measurements make this comparison possible; their stability must also be checked.
Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost
arXiv:2611.03852v1 Announce Type: new Abstract: Reasoning substantially improves language models' ability to solve difficult problems, but long reasoning traces make these gains expensive. Efficient reasoning should express useful analysis in fewer tokens by reducing repetition and text that adds little value to solving the problem. Progress in proprietary models motivates this goal, yet their hidden scratchpads limit direct study of how it is achieved. We investigate whether open-weight models can generate less verbose reasoning by changing the form of their own earlier thoughts, without retraining. Our intervention rewrites prior reasoning into compact state records before pending tool results are revealed, then compares continuations from original and compact histories. Across the tested models, accepted compact histories usually shorten future reasoning; a coding case study also shows less repeated verification after a shared candidate solution. In software-agent deployments, compaction can reduce total spending, although task quality and rewrite-inclusive time depend on the target and compressor. These findings identify reasoning history as one way to reduce future reasoning-token use and motivate model-specific compaction policies evaluated for both efficiency and retained capability.
DouBao Work has officially integrated with DeepSeek, Kimi, and GLM, making enterprise procurement hassle-free.
On October 29, according to Kuai Technology, DouBao Work under ByteDance launched a brand-new third-party large model service for corporate clients. This service breaks the previous practice of companies separately purchasing models from different vendors; users can now seamlessly switch among multiple mainstream large models within the same workspace, tailored to tasks such as long-text processing, code writing, and logical reasoning. The initial rollout includes three industry-leading models.
Anthropic plans to open its IPO subscription to individual investors in the UK and across Europe, aiming to become the largest IPO in history.
Following its filing with the U.S. SEC for a U.S. listing, Anthropic is preparing for a globally watched IPO, planning to list on Nasdaq under the ticker “ANT,” with fundraising potentially setting a new global record. The company also intends to allocate a significant portion of its shares to retail investors worldwide and is reportedly collaborating with a UK-based investment platform to expand into the European market. Further details remain undisclosed.
Instagram modernized its user interface using a native AI architecture, reducing token costs by 33%.
Instagram Direct migrated its Android user interface from the legacy Android View system to Jetpack Compose, creating an AI-native UI codebase that makes it easier for AI coding agents to understand, modify, and maintain.
MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily
MiniMax has open-sourced MCode Stack, an MIT-licensed repo of 17 SKILL.md skills and 5 checklists that its MiniMax Code team uses daily for code review, subagent splits, context budgets and long-running commands. The post MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily appeared first on MarkTechPost.
[AINews] Anthropic ends Coding Interviews: "Hunger beats tenure"
Since coding is solved, why code for the job?
Is the next “big” wave coming? DeepSeek V5 has appeared in the official code repository, with the new-generation flagship model expected to debut in November.
On October 28, users noticed that DeepSeek had once again changed its large-model fingerprint, sparking speculation about the imminent release of a major new model. The official DeepSeek Harness codebase now includes code for DeepSeek-V5, V5-open, and V5-next. Currently, the V5-related content mainly consists of placeholders, but it indicates that the mechanism for releasing the new model is already in place.
AI programming capabilities are reshaping hiring standards, with Anthropic’s head of recruiting scrapping traditional coding interviews.
Felix Rieseberg, Anthropic’s recruitment manager and engineering lead for Claude-related products, stated that his team has eliminated traditional coding‑question interviews, bluntly declaring, “Coding interviews are dead—at least for my team.” He argues that AI tools like Claude can effortlessly tackle small React challenges and even low‑level assembly tasks, diminishing the value of conventional coding tests in distinguishing candidates’ true engineering abilities. As a result, interview outcomes may increasingly reflect the performance of AI tools rather than the candidate’s actual skill level.
Coding From the Himalayas With an Offline AI Agent
How to set up and run an offline coding agent using OpenCode, Ollama and Qwen.
Mirendil Launches Fern 0.1, Its First Model, With 10M-Token Context
Mirendil released Fern 0.1, its first model, pretrained from scratch with a 10M-token context window. It targets agentic AI R&D work, scores 100% on RULER single needle at 10M, but trails frontier models on agentic coding. The post Mirendil Launches Fern 0.1, Its First Model, With 10M-Token Context appeared first on MarkTechPost.
