Hey 👋 we're looking for feedback on the language selector in the post composer. The way it current works is that if you switch languages and create the post, we save your last selection for next time. Would y'all prefer that, or have it reset to your primary language for each new post?
Sep 21, 2026 at 10:24 PM
Opinion | Why Save a Language? (Published 2014)
Hint: It’s not to preserve a different way of seeing the world.
The future of language
These charts will help you choose the language you should focus on today.
Controls as language
A couple of weeks ago, my friend Esteban said some stuff on Twitter that got me thinking (again) about the value of looking at a game’s control scheme as a sort of language. The whole series of tweets is worth a read, but the concluding tweet in p...
I Learned to Speak Four Languages in a Few Years: Here's How
Lifehacker reader Gabriel Wyner was tasked with learning four languages in the past few years for his career as an opera singer, and in the process la
We Should be Able to Change our Languages — Jimmy Miller
It's time we stopped treating languages as sacred fixed objects. We need now, more than ever, languages we can change.
Post-Training Language Models for Crosslingual Consistency
Language models often respond inconsistently to translation-equivalent prompts across languages, undermining the reliability of multilingual systems. To quantify this, we give an information-theoretic definition of crosslingual consistency as a divergence bound between a model's response distribution and its round-trip pushforward across languages. We then introduce penalized consistency optimization (PCO), a post-training procedure that couples this divergence with a Kullback-Leibler penalty to a fixed reference language model. Because direct optimization of PCO requires expensive on-policy roll-outs, we propose a tractable surrogate, direct consistency optimization (DCO), which can be optimized off-policy. Across diverse language models and 26 languages, DCO significantly improves crosslingual consistency, outperforms existing methods, and enables targeted alignment of low-resource languages.
Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via...
Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally...
carbon-lang/docs/project/difficulties_improving_cpp.md at trunk · carbon-language/carbon-lang
Carbon Language's main repository: documents, design, implementation, and related tools. (NOTE: Carbon Language is experimental; see README) - carbon-language/carbon-lang
Laya — 33ms Multilingual System 1 Decision Engine
Evaluates typed decisions (choice, score, noul) over 100+ languages in a single forward pass with calibrated probabilities. Outperforms TypeSafe Jev.
Select a language for A/HRC/32/L.20
dev log #5 - language
Today we get to talk about a topic everybody loves to get excited about - programming languages! More specifically, we're going to talk about the needs when making games with luxe, the landscape of language choices, and the goals of the project being the most relevant decider. Note that the
Prompting Claude Opus 5
Behavioral differences and prompting patterns for Claude Opus 5, covering response verbosity, agentic narration, task scoping, subagent delegation, self-correction, and output artifacts when thinking is disabled.
First Languages AI Reality | Mila
The FLAIR initiative aims to develop a method for the rapid creation of customized ASR models for Indigenous languages.
to add to this, there’s a few product-y reasons why I would really like a createPost API 1. we could run a server-side language detection model that actually works, so we wouldn’t need the language select in the client (it sucks) 2. you wouldn’t need to specify a createdAt time anymore (cont.)
P(aul) Frazee
Nerding out about the question of whether the client or the server should be the one who speaks to the PDS
