Decrypting View State Messages
Article URL: https://zeroed.tech/blog/decrypting-viewstate-messages/ Comments URL: https://news.ycombinator.com/item?id=48821691 Points: 4 # Comments: 3
Latest
OK this is a serious flex the image doesn't make a whole lot of sense (where is she scanning from? she doesn't point at the poster and this isn't a re…
OK this is a serious flexthe image doesn't make a whole lot of sense (where is she scanning from? she doesn't point at the poster and…
Astro 7.0
Article URL: https://astro.build/blog/astro-7/ Comments URL: https://news.ycombinator.com/item?id=48821653 Points: 5 # Comments: 0
Calibrating alignment evals
Currently, alignment evaluation works by constructing a situation, observing the model's behavior and scoring it. We put a lot of thought into designing these benchmarks, and…
Superhuman Articulacy as an LLM Safety Target
TL;DR: Current LLMs are bad communicators relative to their agentic capabilities. I claim that articulacy is useful (and perhaps necessary) for AI safety and suggest a…
Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
Article URL: https://ariya.io/2026/03/local-cpu-friendly-high-quality-tts-text-to-speech-with-kokoro/ Comments URL: https://news.ycombinator.com/item?id=48821576 Points: 3 # Comments: 0
Show HN: Docx-CLI: agents read/edit Word docs using 1/2 the time and tokens
Article URL: https://github.com/kklimuk/docx-cli Comments URL: https://news.ycombinator.com/item?id=48821500 Points: 3 # Comments: 1
Notes on Software Quality
Article URL: https://anthonyhobday.com/blog/20260410 Comments URL: https://news.ycombinator.com/item?id=48821441 Points: 3 # Comments: 0
A new runtime for k and q: l
Article URL: https://lv1.sh/ Comments URL: https://news.ycombinator.com/item?id=48821378 Points: 9 # Comments: 0
RT Alexandr Wang: 1/ releasing muse image today — the first image generation model from MSL. it's agentic: pairs with muse spark to reason through yo…
RT Alexandr Wang1/ releasing muse image today — the first image generation model from MSL. it's agentic: pairs with muse spark to reason through your prompt,…
ACID: Action Consistency via Inverse Dynamics for Planning with World Models
Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close…
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must…
local already feels good enough
This is specifically for coding, technical planning, and hardware setup. _____ The only times Qwen 3.6 35B A3B has let me down, it has been something…
Cohere Transcribe Arabic is an open-source model built for Arabic's toughest transcription problems
Cohere has released Transcribe Arabic, an open-source model for Arabic speech recognition that the company says outperforms Whisper and OmniASR on dialects, code-switching, and bilingual Arabic-English…
Anthropic is launching Claude Cowork on mobile and web
Starting Tuesday, Anthropic's Claude Cowork AI platform will be available on mobile and web for the first time. The expanded access is rolling out first to…
We're extending access to Fable 5 on all paid plans through July 12
https://xcancel.com/claudeai/status/2074548242386178258 Comments URL: https://news.ycombinator.com/item?id=48821102 Points: 59 # Comments: 44
RT Richard Hanania: Incredible WSJ reporting on how European leaders deal with Trump -European leaders workshopped tweets to send Trump, debating whic…
RT Richard HananiaIncredible WSJ reporting on how European leaders deal with Trump-European leaders workshopped tweets to send Trump, debating which words to capitalize. They had to…
The overwrought language of Fable is an ongoing problem in software and design projects where the AI is otherwise excellent. It just creeps into littl…
The overwrought language of Fable is an ongoing problem in software and design projects where the AI is otherwise excellent. It just creeps into little bits…
b9902
[SYCL] support OP cross_entropy_loss, cross_entropy_loss_back (#25236) support OP cross_entropy_loss, cross_entropy_loss_back correct format issue macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
deepest lore
deepest loreMr. S.T.A.R.: A great time to remind everyone about Jack Parsons. A true character: one of the most influential rocket inventors, thelemite occultist, close friend…
RT Tesla: Re With full autonomy and maximized ride-hailing, Cybercab is projected to nearly halve emissions per mile compared to Model 3 + Model Y Als…
RT TeslaRe With full autonomy and maximized ride-hailing, Cybercab is projected to nearly halve emissions per mile compared to Model 3 + Model YAlso, a personal…
Alibaba should actually sweat bullets about this, their strategy can in retrospect be described as “open first, closed later” and it doesn't sound l…
Alibaba should actually sweat bullets about this, their strategy can in retrospect be described as “open first, closed later” and it doesn't sound like Beijing is…
Per-user budgets for cost centers in the billing UI
Enterprise admins can now create cost center user-level budgets directly in the billing UI where you manage cost centers and budgets. This feature is available for…
Enrich your datasets with business context: Migrating from legacy Topics to semantic datasets in Amazon Quick
In this post, we walk through what Dataset Enrichment is, how it differs from legacy Topics, and provide three migration scenarios with step-by-step guidance so you…