Show HN: Why HTTP 200 is lying to your AI agents (and what Postgres did)
Article URL: https://github.com/deedglass/deedglass Comments URL: https://news.ycombinator.com/item?id=50588595 Points: 1 # Comments: 0
Official announcements and industry reporting. Follow the timeline of AI.
From the latest news to tools that work for you.
EvoMap is an infrastructure designed for the reuse of AI agent experiences. It organizes reusable strategies and repair assets with validation records via the GEP protocol, offering market- and quality-based ranking to help different agents discover, evaluate, and inherit existing capabilities.
分类推荐榜首JJAX is a Python numerical computing library designed for accelerators, specifically tailored for high-performance array computations and large-scale machine learning. It efficiently executes the same code across multiple hardware backends, including CPUs, GPUs, and TPUs.
分类推荐榜首M
MemoAIMusic & audioMemoAI is an AI-powered audio-to-text tool that supports localized processing, eliminating the need to upload data and ensuring privacy and security. It can efficiently transcribe YouTube videos, podcasts, and local audio/video files (such as MP4, MP3, AAC, M4A, etc.) into text, while offering core features like multilingual translation, speaker diarization, real-time subtitles, and floating notes—making it ideal for meeting minutes, interview transcription, content learning, and more.
分类推荐榜首OOpenDesign is an open-source design workspace that can connect to local programming agents, use built-in model keys, or leverage cloud-based models, enabling the creation and editing of prototypes, web pages, presentations, and graphics within a design system; local software is free, while model services incur fees.
分类推荐榜首A
AI ShortWriting & contentAIS ALERT MANAGEMENT AND SHARED PLATFORM, QUICK COMMAND FOR MULTIPLE SCENARIOS
分类推荐榜首KKiro is an AI engineering tool for developers that organizes requirements into specifications, architectures, and tasks, generates code via agents, and supports the entire workflow—from planning to code review—through property-based testing, execution memory, and integration with development tools.
分类推荐榜首FCLIENT-ORIENTED AI SMART BODY。
待评分 · 分类列表推荐妙THE AI LIVE TELECOM SOLUTION FROM THE AD
待评分 · 分类列表推荐E
ElicitKnowledge & researchElicit provides semantic search, research report generation, literature screening, and data extraction for scientific research. It enables traceable answers within source materials and organizes evidence through a literature library, research agents, and ongoing tracking workflows, making it ideal for advancing from initial problem exploration to systematic reviews.
待评分 · 分类列表推荐AAssemblyAI is a speech AI platform for developers, offering pre-recorded, real-time, and short-form synchronous transcription APIs. It enables the building of voice-based applications by integrating capabilities such as speaker identification, emotion analysis, chapter and summary extraction, as well as speech agent functionality, dictation, and sensitive information processing.
待评分 · 分类列表推荐Article URL: https://github.com/deedglass/deedglass Comments URL: https://news.ycombinator.com/item?id=50588595 Points: 1 # Comments: 0
Article URL: https://pockettransfer.app/ Comments URL: https://news.ycombinator.com/item?id=50587486 Points: 1 # Comments: 0
Article URL: https://www.rmrfbench.com/ Comments URL: https://news.ycombinator.com/item?id=50587178 Points: 1 # Comments: 1
I’m writing my first novel and could not find an app that fit my workflow: quiet like iA Writer, organized like Scrivener, and with AI so I can discuss my book while I write it. It allows me to feel less “alone” and have a sounding board while I write.- A book is a folder of plain Markdown files. Musset commits to a git repo, tracks versions and drafts without you having to know git.- Revisions are CriticMarkup inside the text. It manages docx revisions too, so your editor can edit a Word doc and you import their comments.- PDFs are typeset using Typst, embedded in the app, following each language’s typographic rules.- Spelling and grammar are checked using LanguageTool, also embedded.- Mac/Word, WordStar, vi and Emacs keyboard modes.The AI is optional and uses your Codex or Claude Code CLI. It comments, leaves margin notes, and checks continuity and your chapters against your style rules.It’s GPL-3.0 and free during the beta. When or if it reaches 1.0, if there is sufficient interest, the idea is to make it a small one-time payment ($9.90). There is a paid sync service (git hosting) that lets you share a book with beta readers and editors.Download: https://musset.appI’d love to have some feedback! Comments URL: https://news.ycombinator.com/item?id=50586323 Points: 2 # Comments: 0
A personal project for digging deeper into Linux system programming, ObFUSEcate implements a file backed virtual block device that automatically performs compression and encryption as blocks are accessed. This virtual device can be mounted via FUSE (requiring no root privileges) to provide, effectively, a "live" compressed, encrypted archive.Written in C++, and intended to have minimal dependencies, it has custom 32 bit arithmetic encoding/decoding, ChaCha20-Poly1305 authenticated encryption, and CRC8 + XOR parity error-correction. Comments URL: https://news.ycombinator.com/item?id=50585222 Points: 1 # Comments: 0
Hi HN,I wanted a PDF viewer I could drive entirely from the keyboard that could also fill in forms and sign documents.You might already be acquainted with PDF viewers like zathura and sioyek. This one is similar, except much more performant and not prone to crashes. You can also draw, annotate and fill & sign entirely via keyboard.It's based off of PdfCraft's (from the ArtCraft project) rendering engine.The config is configured in TOML and live-reloaded.Feel free to try and give feedback. Comments URL: https://news.ycombinator.com/item?id=50584936 Points: 1 # Comments: 0
AI operational readiness requires more than selecting the right servers, storage and computing capacity. Those considerations are particularly consequential for financial institutions, where reliability, regulatory obligations and the need to demonstrate returns on technology investments shape deployment decisions. Meanwhile, AI is changing the threat landscape, giving less sophisticated attackers access to capabilities that once required […] The post Three insights you may have missed from theCUBE’s coverage of the Dell Technologies New York Symposium appeared first on SiliconANGLE.
Article URL: https://github.com/SwordSec/SwordCheck Comments URL: https://news.ycombinator.com/item?id=50582903 Points: 1 # Comments: 0
Article URL: https://github.com/JustVugg/nostromo Comments URL: https://news.ycombinator.com/item?id=50579736 Points: 1 # Comments: 0
Article URL: https://netsieve.app/ Comments URL: https://news.ycombinator.com/item?id=50579335 Points: 1 # Comments: 0
Article URL: https://play.outbid.sh Comments URL: https://news.ycombinator.com/item?id=50578763 Points: 1 # Comments: 0
I've seen too many slow-log queries with a GROUP BY that makes Postgres blow up, so for the last two weeks or so I've been working on Straum. You declare the aggregates as a view, and Straum answers over HTTP (other transports might be added). I've been using the New York taxi dataset as a benchmark. On the heavier GROUP BYs I see about 1,000x to 5,000x. It's written in Rust (of course).It leans on Postgres replication slots, logical or physical, to get its data. Postgres stays the source of truth.Benchmark: https://janbjorge.github.io/straum/benchmark.html Repo: https://github.com/janbjorge/straum Comments URL: https://news.ycombinator.com/item?id=50578332 Points: 1 # Comments: 0
What if solar farms could keep generating electricity after sunset with a little help from mirrors orbiting Earth? Or researchers could send an experiment into space for less than the price of a car? Our latest roundup also includes a company bringing AI to the old-school business of garbage hauling, another rethinking how factories are programmed, and a consumer brand betting that better breathing could become a big business.
Growing fintechs struggle with a divided funding landscape, while later-stage companies face delays due to an IPO backlog, prompting investor interest in younger startups as a source of optimism.
arXiv:2611.25003v1 Announce Type: new Abstract: Language models often produce high-quality individual samples but poor sets, with repeated samples clustering around the same semantic modes. We formalize diverse generation as sampling a size-$K$ subset of complete strings from a determinantal point process (DPP), where the likelihood encodes item quality, and the embedding geometry encodes repulsion between similar outputs. Exact inference over all strings is intractable, so we propose PoolDPP: draw a finite candidate pool from a tractable proposal, importance-weight the candidates toward the target quality, and run a $K$-DPP sampler on the induced pool kernel; a greedy MAP variant provides deterministic selection. We prove a finite-sample bound with an explicit constant: the KL divergence between the sampler's output and the target $K$-DPP decays as O(1/N) in the pool size. Empirically, PoolDPP extends the quality--diversity frontier on open-ended generation and the precision--recall frontier on ambiguous text-to-SQL (Ambrosia), and on mathematical reasoning (GSM8K), it raises diversity at about the same pass@$K$.
arXiv:2611.25236v1 Announce Type: new Abstract: Unplanned 30-day readmissions among patients with diabetes mellitus impose a substantial clinical and economic burden, yet most predictive models use only structured electronic health record (EHR) data and ignore free-text clinical notes, which often contain code-mixed Hindi-English (Hinglish) phrasing and negation that general-purpose language models parse unreliably. We propose a neurosymbolic multimodal framework evaluated on the public Diabetes 130-US Hospitals dataset (101,766 encounters; 71,518 patients) with a patient-level grouped 80/20 split. Three streams are fused: engineered structured features; 32 components of Bio_ClinicalBERT note embeddings obtained by truncated singular value decomposition; and symbolic entities extracted by an open-weight clinical language model within a three-stage hybrid retrieval-augmented generation pipeline (dense retrieval, sparse lexical retrieval, and cross-encoder re-ranking) with reflective negation auditing. A cost-sensitive XGBoost classifier with a decision threshold calibrated by Youden's J statistic produces the prediction. On the held-out test cohort (n = 20,153), the structured baseline achieved an area under the receiver operating characteristic curve (AUROC) of 0.6477, sensitivity of 0.5839, and Brier score of 0.1080. The full multimodal model achieved the highest sensitivity (0.6667; +8.28 percentage points), the best F2-score (0.3824), and the lowest Brier score (0.0977), at a slightly lower AUROC (0.6375) and specificity (0.5161). Shapley additive explanations showed that prior utilization dominates risk, with compressed narrative components among the top predictors. On a 500-note code-switched benchmark, grounded retrieval raised Hinglish symptom recall from 4.8% to 40.2% and precision from 3.1% to 45.2%, while reducing entity hallucinations from 1.74 to 0.00 per note.
arXiv:2611.25171v1 Announce Type: new Abstract: Test-time compute (TTC) improves language models by spending additional inference compute to generate, verify, and select among candidate outputs, but this recipe has not transferred directly to time series forecasting. A language model can verify a proof or vote across samples, but a forecaster must be causal; it cannot use future information to score a candidate. We propose Backtest-Gated Augmentation Averaging (BGAA), a TTC algorithm for time series forecasting that builds a causal verifier from the series's own history, using rolling-origin backtests to score structured views of the context, discard those that underperform the untransformed context, and average the survivors' predictive distributions. BGAA improves every tested TSFM-benchmark combination, reducing MASE by 0.5-1.0% on GIFT-Eval, 1.3-5.0% on fev-bench, and 1.7-5.9% on BOOM, where a 313M model with TTC outperforms the 1B and 2.5B models in its family. We further show that useful views have structured, model-dependent effects consistent with a prior-transport interpretation. On the 53 cross-fittable GIFT-Eval configs, the deployed policy gains only 0.4-1.3% CRPS, versus 1.4-4.1% when choosing the best view for each dataset configuration and 17-19% when choosing the best view separately for each test window. This gap suggests that a major remaining challenge is window-level view selection.
Amazon Bedrock AgentCore harness now runs on the open-source Strands harness, bringing a recommended model, task-oriented defaults, automatic prompt caching, proactive context management, and new built-in tools. It also adds lifecycle hooks so you can run deterministic allow or deny checks at defined points in the agent loop.
Article URL: https://www.robertpeake.com/archives/104254-ai-came-for-the-coders-understanding-why-tells-us-whos-next.html Comments URL: https://news.ycombinator.com/item?id=50563328 Points: 20 # Comments: 14
Give your curiosity direction. Make every day of reading count.