Erwin (@eres2k) header
Erwin (@eres2k) profile picture

I lIke AI

Wien, Österreich
Joined June 2009
Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)Photo by Erwin (@eres2k)
[🪄 #GIVEAWAY🪄 ] À l'occasion de la sortie officielle du DLSS 5 dans Hogwarts Legacy, tentez de GAGNER une NVIDIA GeForce RTX 5090 customisée aux couleurs du jeu ! Comment PARTICIPER ? 💬 Commentez avec #RTXON 🔁 Partagez ce post
12,052
11,696
198
7,736
731,227
Erwin retweeted
Replying to @nytimes
Created with Nvidia RTX5090 😭
16
82
13
1,449
155,841
Should I feel bad that I used Nvidia Hardware for this? @nvidia @JensenHuang
1
4,487
My 2020 LG Oled TV now runs a custom launcher as well. Tesla, Hue, Roborock, Email and calendar integration. One Dashboard, built for the remote. Created with GPT-Astra. #webos #GPT
2
224
Jev isn't an LLM — one parallel pass per decision, no reasoning at all. I put it on a chess board vs my local Qwen 3.8 27B (reasoning:off) stack on my 5090. Playing on pure single-pass judgment, Jev navigated a tactical bloodbath and came out with rook + bishop + 3 pawns vs a lone king. +11 material against a full language model. Then ten checks, no mate. Draw. 337 ms/move, twice as fast my local Qwen stack at 700ms. Full Article: teapaw.org/eres2k/status/21004691… @typesafeai @CompleteSkeptic
3
367
Qwen3.8-27B with DFlash2 at 215 tok/s on one RTX 5090 — 2.3× past what the memory bandwidth should allow! Settings below.
2
4
336
Meine PAF ist tatsächlich 11 hz 🥰
8
1
16
3,903