Updated
Updated
Items with an AI score under 20 are hidden. Show low-relevance items
Viktor Oddy@viktoroddyXAI score22AIA post introduces Restyles, a tool where users enter a prompt and specify a target style, and the prompt rebuilds itself accordingly. The author demonstrates the process four times in a video and promotes a free trial at
Nace AI@NaceAIXAI score22AINACE introduces NDI 1.0, a document processing model for coding agents that it says is 90% cheaper and ranks first on the Parse Index. The company says it offers native MCP, SDK, and CLI integration for Claude Code, Codex, Hermes, OpenClaw, and PI, and supports 50 languages. NACE also states the model was trained on over 15M financial files and offers $25 in free API credits to developers.
AISimon Willison has released ttok 0.4, a command-line tool for counting tokens built on OpenAI's open source tiktoken library. The update adds a --list-models command, fixes a Click warning, and updates CI, and the tool can run through uvx, for example with cat file.txt | uvx ttok.
Rahul@sairahul1XAI score25AIA solo founder used Teamily AI, a platform where humans and AI agents share one group chat, to automate a multi-step project. A research agent analyzed the author's 20 most-saved posts, a writer agent drafted content, a web agent built a live website in Website Builder, and a custom Verification Editor agent blocked the launch twice over a misquoted Anthropic doc. The team can be saved as a Loop that reruns weekly and waits for human approval before publishing.
elvis@omarsar0XAI score32AIFish Audio's Drama 3 voice model lets users direct tone, emotion, and pacing in plain language, and can shift emotion mid-sentence. The poster, who found it remarkably effective in testing, says the control over delivery is unlike anything previously seen. A preview is available through the API as drama-3-preview.
AITessl's Code Review defines review standards as skills in the repository, called lenses, routed to files by a repo-owned profile file. Because these team-visible standards are portable, lessons from review can feed back into code generation and maintenance, not only the next review.
AIUnsloth Studio binds remote-code approval to a fingerprint of the scanned code, so changed code requires fresh consent before it runs. It also blocks weight files that Hugging Face has flagged for malware in the path the selected loader would deserialize. The article describes these checks as one layer among several, alongside package-content scans and OS sandboxes, and notes that the scanner is not a sandbox and cannot catch every evasion.
Sara Hooker@sarahookrXAI score36AIAdaption Labs has launched Invent-a-dataset, which creates post-training datasets from a natural language description alone. A technical report compares the Invent API against frontier proprietary and open-weight LLMs used for data generation. Sara Hooker's post links to the launch page and the report's technical details.
AITerse, a Claude Code plugin, enforces a shorter reply style by cutting filler, slogans, metaphors and first-person narration. The author says it reduces replies by 46% on Fable 5.1 and 54% on Opus 5.5, measured on 20 prompts against a real codebase. The plugin installs from the Claude directory or GitHub, and its rules apply to replies, documents, commits and subagents.
Daniel Han@danielhanchenXAI score48AIUnsloth now lets users train their own decision models locally on just 3GB of VRAM by fine-tuning Qwen, Gemma, and Llama with a Clef head. The post says this raises accuracy from 30% to as high as 78%, and the tool is available through Unsloth Desktop.
elvis@omarsar0XAI score36AIDAIR.AI has introduced MCP tools that let Codex, Claude, or Grok bots discover and explore a curated index of top AI papers. The index covers papers the author featured on X over the last couple of years, and the tools support summarizing papers, building literature reviews, finding SOTA results, and visualizing papers. Further benchmarks and regular additions are promised in the coming weeks.
Orange AI@oran_geXAI score35AIOrange AI released "podcast-to-article," a free MIT-licensed open-source skill that reorganizes podcast transcripts by topic rather than speaker timeline. The author says it keeps every number and original quote while cutting off-topic tangents, and that early readership and engagement were good.
Teknium 🪽@TekniumXAI score20AITeknium says a plugin from @altryne's current project should be added to the plugin catalog. The post is a brief endorsement and does not describe the plugin's functions. Background from @tonysimons_ says Hermes is getting a local video editor for editing user footage with 42 FFmpeg scripts and no cloud or API key required.
AIEvery launched the Every Agent, a Slack-based agentic coworker whose token costs it passes on to customers without markup. Engineer Paridhi Agarwal explains how she made the agent more token-efficient, and the newsletter says the company moved from personal agents to a single shared company agent.
Thariq@trq212XAI score22AIThariq, who works at Anthropic, is developing a skill for Claude Code that produces HTML plans using simple language, code snippets, surfaced questions, and mockups. Linting is used to reduce common failure cases Claude encounters, and he is seeking feedback before a broader release.
Google for Developers@googledevsOfficialAI score22AIMatthew Tait built a Chrome extension that listens to students reading aloud and delivers instant phoneme-level pronunciation diagnostics. The tool is aimed at supporting reading comprehension. The post was shared by Google for Developers in reply to Antigravity.
Ideogram@ideogram_aiOfficialAI score20AIIdeogram 4.5 can convert famous paintings into realistic photographic scenes using the single prompt "Turn this painting into a realistic scene." The example shown is Edvard Munch's The Scream (1893), reimagined as a photo.
Prime Intellect@PrimeIntellectOfficialAI score32AIExtropic post-trained Qwen3.6-35B-A3B with Prime Intellect for thermodynamic ML research, nearly tripling its held-out eval results in about 100 GRPO steps. The team built a custom RL environment with verifiers and trained on Hosted Training, Prime Sandboxes, and Prime Inference. This let Extropic avoid managing multi-node GPU infrastructure and focus on research.
Ideogram@ideogram_aiOfficialAI score25AIIdeogram 4.5 turns a single room photo into a design canvas where furnishings, finishes, and palettes can be swapped one edit at a time. The room's architecture stays unchanged throughout the edits.
AIVespper, a Y Combinator F24 startup, launches a DOCX MCP that lets agents edit Word files through HTML that a trained reconciler converts back to OOXML. On its 279-task internal benchmark, the company reports its MCP is 2.7–2.9x cheaper and 2.7–3.5x faster than Anthropic's DOCX skill, with higher pass rates. The post also lists current limitations, including no comment creation or reply, no image or video attachment, and no support for latent styles.
hardmaru@hardmaruXAI score30AIThe authors announced that their Neuroevolution textbook is now in print, with a free online edition and pre-orders available. The post frames the book's ideas on open-ended creativity and self-organizing systems as the theoretical foundation of Sakana AI's work.
AIMastra now offers classifiers that use evaluation models to answer questions defined as choice, score, or boolean, returning criteria keys, ordered positions, or true probabilities. Classifiers are registered on the Mastra instance and can drive workflow branching, such as routing a request to one of several agents. The feature requires @mastra/core 1.69.0 or later.
OpenClaw🦞@openclawOfficialAI score22AIOpenClaw has updated how plugins load, enabling hot reloading so sessions keep running while changes take effect. The update was made by Patrick Erichsen alongside several other improvements, with a live demo showing an Apple PIM plugin installed and built on the fly.
vLLM@vllm_projectOfficialAI score30AIvLLM has published a blog post explaining how its integration with TileRT works, alongside a public benchmark configuration in the InferenceX repository. The benchmark script covers GLM-5.3 FP8 on MI355X hardware and is linked on GitHub. The post itself provides the integration details.
AIvLLM now supports Gumbel-max watermarking, which embeds a keyed signal into generated text without changing the expected token distribution. Detection requires the secret key and tokenizer, and the signal accumulates over longer outputs. Benchmarks on Qwen3.5-27B with MTP-3 show throughput changes between -1.1% and +2.0% across batch sizes, with no consistent slowdown.
OpenBMB@OpenBMBOfficialAI score34AIA research-agent design has GPT-6 orchestrating while MiniCPM5-2B runs locally on DGX Spark to read sources and extract traceable evidence. The post presents this as an example of pairing frontier reasoning with compact, efficient models for transparent research workflows.
LM Studio@lmstudioOfficialAI score44AILM Studio's new Introspection feature lets its Bionic agent search its own session history, improving handling of long-term context across multiple compactions. Users can also reference other sessions directly in the composer with an @ mention.
Tinker@tinkerapiOfficialAI score32AISundial fine-tuned Thinking Machines' Inkling-Small with RLVR on 3,978 verified TeX.StackExchange fixes, using rewards for compilation and PDF match and penalties for removed content. The trained model fixes 83.7% of LaTeX errors in under one second at $0.0013 per fix, according to the post. Sundial says it is rolling out the model in its editor, applying fixes as suggestions and rebuilding the PDF.
ollama@ollamaOfficialAI score22AIOllama says users can enable ChatGPT inside its app, with downloads available at The post gives no further details on how the integration works or which models it covers.
RadixArk@radixarkOfficialAI score22AIRadixArk has published a cookbook on its Miles documentation site covering how to run DeepSeek V4.1 Flash. The post itself contains only a link to the cookbook page, so no further details about features, figures, or setup steps are available.