Local Inference maniac, now I spend more time exploring Agentic Engineering than gaming
0xMX
Joined February 2009
- Tweets48.4K
- Following1.1K
- Followers894
- Likes75.7K
Pinned Tweet
“Remember: Everything fails, all the time, so plan for failure and nothing fails.”
- @Werner
Glitch 81 ᯅ retweeted
We’re releasing new Qwen3.8-Flash-Next GGUFs with 15% higher accuracy.
Unsloth Dynamic V3.1 outperforms others by >15% on Terminal Bench, DeepSWE & more benchmarks (256K context).
Run on 32GB+ RAM setups.
GGUF: huggingface.co/unsloth/Qwen3…
Blog: unsloth.ai/docs/models/qwen3…
Glitch 81 ᯅ retweeted
We expanded the NVIDIA Agent Toolkit to help developers build agents that use company data to answer questions and make predictions, with controls over what agents can access and do.
Watch how @LilaSciences , @Siemens and @Dassault3DS are using AI agents to design potential therapies, plan factory production and refine vehicle designs.
See what’s new → nvda.ws/4BJ7VrE
Glitch 81 ᯅ retweeted
> be AI company
> scrape the entire internet
> ignore licenses and copyright
> download millions of pirated books
> use them to train frontier models
> spend tens of millions buying physical books
> cut off their spines
> scan every page
> destroy the originals
> lecture everyone else about intellectual property
> we are the good guys
We added two sentences to Claude Code's prompt on Opus 5.5 to steer it away from recreating someone else's specific game because using Claude to infringe IP is against our usage policy.
Original games, genre games, and games built from your own designs and assets are meant to keep working.
We'll continue to iterate to ensure we're striking the right balance. In the meantime, if Claude turns down something that's yours, send it my way.
Glitch 81 ᯅ retweeted
Software engineers love saying that AI-generated code is unmaintainable.
But let's not pretend the code humans have been writing for the last 30 years has been some masterpiece of maintainability.
I just can’t believe there still people buying @Raspberry_Pi
Raspberry Pi hikes prices again, with the Raspberry Pi 5 16GB hitting an eye-watering $385. hackster.io/news/raspberry-p…
Glitch 81 ᯅ retweeted
Spamhaus is changing the rules in November.
Every sending IP needs a valid HELO, reverse DNS and a matching A record, or it's a candidate for listing
If you run SMTP, this is your deadline. Here's everything that changed and the exact checklist to fix it
Glitch 81 ᯅ retweeted
So, the French socialists, and Parliament members just voted a tax, that they don’t understand, which would cost VideoLAN more than 1 million euro per year.
They are probably the most clueless politician on Earth? And they claim they want technological sovereignty…
@LaurentLhardit
#PJL2027 Adopté par l'Assemblée nationale : la "taxe assise sur les flux de données numériques émises par les fournisseurs de contenu et acquittée par ces derniers"
Selon les députés PS, "au taux de 0,055 € par giga, un rendement de 10Md€ est attendu".
assemblee-nationale.fr/dyn/1…
Glitch 81 ᯅ retweeted
BREAKING: 🇫🇷 French lawmakers just voted 11-10 in favour to introduce a tax on internet data.
If approved, Netflix, Youtube, Meta and all internet businesses will have to pay a tax of 5.5 cents for every GB users consume in France.
That’s nearly $12 Billion in new revenue for the government.
Glitch 81 ᯅ retweeted
🚨 0.77€ de taxe pour regarder un film Netflix !
Ce vendredi, les députés viennent d'adopter un amendement socialiste visant à taxer les données qui circulent sur Internet à hauteur de 5,5 centimes par gigaoctet reçu en France.
Ils ont complètement pété les plombs.
Voici quelques exemples de ce que ça va désormais vous coûter :
🔴 Vous regardez un film Netflix de 2 heures en 4K ? Jusqu'à 0,77 € de taxe brute sur les données transmises.
🔴 Vous téléchargez un jeu vidéo de 150 Go ? 8,25 €.
🔴 Vous récupérez 200 Go de photos personnelles stockées chez Google ? 11 €.
🔴 Vous rapatriez 1 To de vos propres fichiers depuis Google Drive ? 55 €.
🔴 Vous restaurez 2 To de sauvegardes après une panne informatique ? 110 €.
Ces taxes seront facturées aux plateformes américaines, qui vous vous en doutez bien, vous redescendront la facture !
Ils sont en train de construire une fiscalité qui pénalise le simple fait de transmettre de la donnée.
Et ceci alors que nous sommes à l'aube d'une révolution technologique majeure avec l'IA !
Pour rester compétitifs, tous les pays doivent accélérer leur transformation numérique.
Et nous en France, que trouve-t-on comme idée de génie ?
UNE PUTAIN DE TAXE SUR LA DATA !
Et en plus ils ont le culot de nous la présenter comme une mesure écologique qui encouragerait à réduire les volumes de données échangées.
Quelle bande de guignols.
Il faut être totalement déconnecté des réalités économiques pour considérer qu'un pays peut retrouver sa prospérité en multipliant indéfiniment les prélèvements sur les activités productives.
Cet amendement n'est pas encore une loi définitive, mais le simple fait qu'une telle proposition ait été adoptée à l'Assemblée nationale en dit long sur la manière dont nous sommes gouvernés.
Ces fous du bus vont vraiment nous mettre au fond du ravin.
People is using ddr3 machines to run models at a surprising speed 🫡
Old DDR3 Xeons are supposed to be e-waste for local AI.
75 tok/s. Qwen 3.8 Flash Next, a 180B model, answering after a 172K-token prompt.
The box: two Xeon E5-2670 v2 with no AVX2, 64 GB of DDR3, PCIe 2.0. And 2x CMP 50HX mining cards, memory-modded from 10 GB to 20 GB each.
On 1 October Strata refused any CPU without AVX2. On 4 October it ran them.
xrip measured this box on his own build of Strata 0.2.0: 65.5 tok/s by default, 75.1 with 19 CPU workers, six runs.
Why it works: 98% of the experts sit on the 2x mining cards. The old CPU computes the other 2%.
Which old Xeons run it, and the October fight that got Strata there: Issue 2 of The Local LLM Sizing Guide, out tomorrow.
vramcalculator.com/sizing-gu…
Glitch 81 ᯅ retweeted
LFM3-VL-2B vs Gemma 4 E2B on 50 real scanned receipts.
LFM3 got 41 of 50 receipts fully right. Gemma got 28. 50 receipts from SROIE, same prompt, JSON out, one 5060 Ti 16 GB.
- LFM3-VL-2B: 95% of fields right, 41/50 receipts perfect, 46 s
- Gemma 4 E2B: 87% of fields right, 28/50 receipts perfect, 62 s
Across both tests: Gemma reads messy chat-style text a bit better (95% vs 90%). LFM3 reads receipts better, and was faster both times.
@liquidai @googlegemma
Introducing 𝙻𝙵𝙼𝟹: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.
> 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.
> 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱: text, 256k context window.
> 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱: vision-language model with video-input support for spatial understanding
> 𝙻𝙵𝙼𝟹-𝙰𝚞𝚍𝚒𝚘-𝟸𝙱: tool calls, voice chat, reasoning in 18 languages.
> 𝙻𝙵𝙼𝟹-𝙾𝚖𝚗𝚒-𝟸𝙱: an omni model combines vision, audio, and language.
> 𝚍𝟷-𝟸𝙱 and 𝚍𝟷-𝙾𝚖𝚗𝚒-𝟸𝙱: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.
> fine-tune on 1 GPU.
> a new tri-hybrid architecture
> architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.
> 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱 is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.
> 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱 is #1 on the Pareto frontier of device intelligence 𝚙𝚒𝚙𝚎𝚝𝚝𝚎.𝚕𝚒𝚚𝚞𝚒𝚍.𝚊𝚒
Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.
1/ 🧵
Glitch 81 ᯅ retweeted
CUDA Live: Introduction to CUDA Rust teapawt.org/i/broadcasts/1RKZzBapW…