I've wanted a voice AI to let me go through my emails on the way to work for years. GPT 5.4 just one-shotted it. github.com/tomblomfield/voic…
→ View original post on X — @scobleizer, 2026-04-06 03:26 UTC
CODE
-
Running OpenClaw on TempleOS Instead of Discord
By
–
Forget Discord, this is how I’m running my OpenClaw from now on. I want nothing else in life https://t.co/bsY0Dv181h
— Shadow (@4shadowed) 6 avril 2026Forget Discord, this is how I’m running my OpenClaw from now on. I want nothing else in life the cutest Ξngineer (@0xQTpie) a workaround for this is if you run third-party harnesses like OpenClaw inside TempleOS, the power of HolyC and God forbids Anthropic from blocking your claude subscription (it's an exception in their Terms of Service) but it does make your opus act a little weird though… — https://nitter.net/0xQTpie/status/2040942206014419406#m
-
How to Solve Data Analytics Problems with Python
By
–
How Do You Solve #DataAnalytics Problem?
by @Python_Dv #DataScience #BigData -
AI agents can now run Stockfish at 3650 Elo
By
–
Yet your agents can run Stockfish with an Elo of 3650
-
Google Veo 3.1 Lite Cuts AI Video Costs and Coding Gets Hands-Off Upgrade
By
–
AI video just got a massive price cut, and coding just got a "hands-off" upgrade. The Big News: Google Veo 3.1 Lite: Google just slashed the cost barrier for AI video. Developers can now build high-volume video apps at less than half the price of Veo 3.1 Fast, without
-
pi-share-hf: Share Coding Agent Sessions on Hugging Face
By
–
Putting my tokens where my mouth is. I built pi-share-hf. Share your pi coding agent sessions as @huggingface datasets.https://t.co/ue9TWaIfrM
— Mario Zechner (@badlogicgames) 6 avril 2026
It tries to prevent you from uploading sessions containing PII/sensitive data with 3 tiers of defenses. Best used on OSS coding… https://t.co/92A1TneyIG pic.twitter.com/DCshnqxCZ3Putting my tokens where my mouth is. I built pi-share-hf. Share your pi coding agent sessions as @huggingface datasets. github.com/badlogic/pi-share… It tries to prevent you from uploading sessions containing PII/sensitive data with 3 tiers of defenses. Best used on OSS coding sessions, as those are less likely to contain sensitive info. Uses pi agents for PII detection, which can cost you a lot of tokens. Read the README with your human eyes so you don't accidentally pwn yourself or get a huge bill. Haven't figured out how to filter for such datasets on HF yet. @ClementDelangue, any pointers on how to best label them so people can find them? Mario Zechner (@badlogicgames) we as software engineers are becoming beholden to a handful of well funded corportations. while they are our "friends" now, that may change due to incentives. i'm very uncomfortable with that. i believe we need to band together as a community and create a public, free to use repository of real-world (coding) agent sessions/traces. I want small labs, startups, and tinkerers to have access to the same data the big folks currently gobble up from all of us. So we, as a community, can do what e.g. Cursor does below, and take back a little bit of control again. Who's with me? cursor.com/blog/real-time-rl… — https://nitter.net/badlogicgames/status/2037811643774652911#m
→ View original post on X — @clementdelangue, 2026-04-06 02:27 UTC
-
Model Context Protocol and Context Layer Architecture
By
–
The context layer, or more precisely the model context layer, and thus .. the model context protocol
-
Diamond Hacks Award: ADA Compliance Platform with Browser Use Agents
By
–
just won best use of browser use at diamond hacks!
— clarissa 🛋️ (@0xCL4R) 6 avril 2026
we made an ADA compliance analysis and 3D immersive platform for people who have mobility impairments. we implemented gaussian splatting for interior view and deployed Browser Use agents for compliance check + annotation.… pic.twitter.com/tC49zquk3Kjust won best use of browser use at diamond hacks! we made an ADA compliance analysis and 3D immersive platform for people who have mobility impairments. we implemented gaussian splatting for interior view and deployed Browser Use agents for compliance check + annotation. (thanks @browser_use + @reagan_hsu for the opportunity and iphone, crazy timing cause im out of storage)
→ View original post on X — @scobleizer, 2026-04-06 01:14 UTC
-
SHINE: Hypernetwork Generates LoRA Adapters from Context Instantly
By
–
What if LLMs could instantly absorb new context directly into their parameters? Researchers from Peking University, University of Oxford, Technion, and NVIDIA present SHINE! SHINE is an innovative hypernetwork that, in a single pass, generates high-quality LoRA adapters directly from diverse contexts. This effectively bakes temporary contextual knowledge into the LLM’s core parameters, turning it into lasting skill without any traditional fine-tuning. It smartly reuses the LLM's own frozen parameters for efficiency. This breakthrough dramatically cuts down on time, computation, and memory costs compared to supervised fine-tuning (SFT). SHINE outperforms SFT across various tasks, especially in complex question answering by embedding knowledge directly, offering outstanding performance and massive scalability potential. SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass arXiv: arxiv.org/abs/2602.06358 GitHub: github.com/Yewei-Liu/SHINE Hugging Face: huggingface.co/collections/Y… Our report: mp.weixin.qq.com/s/sy1L2RoWu… 📬 #PapersAccepted by Jiqizhixin
→ View original post on X — @jiqizhixin, 2026-04-06 01:11 UTC
-
Hermes Agent Generates 3Blue1Brown Style Math Animations Automatically
By
–
🚨 ESTO ES UNA LOCURA ABSOLUTA
— Erick (@ErickSky) 6 avril 2026
Ahora le dices a Hermes Agent un concepto matemático cualquiera… y te genera una animación exacta estilo 3Blue1Brown en segundos.
Esto democratiza el contenido educativo de nivel élite.
El futuro de enseñar (y aprender) ya llegó. https://t.co/FAvGi2c7Rq🚨 THIS IS ABSOLUTELY INSANE Now you just tell Hermes Agent any mathematical concept… and it generates an exact 3Blue1Brown-style animation in seconds. This democratizes elite-level educational content. The future of teaching (and learning) is already here. — Nous Research (@NousResearch) Introducing the Manim skill for Hermes Agent. Manim is an engine for creating precise programmatic animations for mathematical and technical explainers, made famous by the @3blue1brown channel. [Video] — https://nitter.net/NousResearch/status/2040931043658567916#m [Translated from EN to English]
→ View original post on X — @scobleizer, 2026-04-06 00:54 UTC