Deano Calver (@DeanoC) header
Deano Calver (@DeanoC) profile picture

MTS@Geometric - AI auto-optimizing GPU kernels Co-creator with @julian_gollop of Chip 'n Clawz Prev Silent Hill 2, Brink, Heavenly Sword, Phoenix Point, Apple

Sofia, Bulgaria
Joined March 2007
Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)Photo by Deano Calver (@DeanoC)
Replying to @DeanoC
I’ve been building in this space here: github.com/DeanoC Current project: github.com/DeanoC/Spiderweb - My distributed hosted OS for any AI agent github.com/DeanoC/SpiderMonk… - Custom agent specialized to Spiderweb (demos / videos coming shortly)
2
5
1,058
1
2
9
443
My FES 100Mhz 386 fpga core (from scratch) can play wolf3D!! Milestone reached, soon can it play doom will be answered!
2
1
5
255
Work in progress still but if you can't name the game, can you call your self a retro gamer?
1
1
24
Amusingly and fitting, it wasn't the emulator that took a while to get it working it was DOS config :D Using FreeDOS doesn't load Ultima 7 without work. Just like the old days, got to edit that autoexec.bat and config.sys files 😜
11
With #GTA6 nearing launch, it's worth remembering where it all started. This first image spawned the first prototype, which in turn helped spawn the second. And the rest as they say.... is history. You can see a printout of this image, just over my shoulder. This picture was taken while making the prototypes, sometime in 1994. #GTA @gtacommunitysol solana:2wMTr4ZttVr5tmS4wLStee59wi8f9QQfMtT2Hoispump
27
97
5
942
36,822
My FES XT FPGA core (seperate from my 386 core shown earlier!) can play Digger! Two seperate FPGA x86 cores from scratch at the same time! Now tell me AI is useless in the hands of a experience developers!
2
135
Stripe is not impressed with my cable management. Inventory: Desktop Intel CPU + 2 AMD GPU Super station one (DE10-nano FPGA) Mister Pi (DE10-nano FPGA) 2 x DE25-nano fpga 2 x HDMI -> USBC 1 x HDMI -> USB2 White The Spectrum + Joystick Old Apple Mouse 2 x Cat advent calenders
1
207
Deano Calver retweeted
Day 25/ We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today. We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage. And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
7,386
2,678
3,626
38,715
7,016,310
Deano Calver retweeted
Five years ago, I released Air Hockey Arcade for Meta Quest. Today, I'm excited to introduce its next evolution: Air Hockey XR! 🏒🥽 Built for Mixed Reality, with hand tracking, a full single-player campaign and a whole lot of arcade personality. Available now on Google Play for XREAL Aura and other Android XR devices, with more XR platforms to follow!
6
6
25
2,772
Deano Calver retweeted
Two cult horror classics have emerged from the shadows – Ecstatica and Ecstatica II are now available on GOG! These pioneering survival horror adventures have been lovingly prepared by SNEG to run smoothly on modern hardware, so their eerie worlds can haunt a new generation of players. Ready to face your fears? Discover both Ecstatica games on GOG and keep gaming history alive: bit.ly/4zV0OKV
18
116
11
889
31,822
AI agentic have made forks so much easier, its basically trivial to keep your fork upto date with the upstream, which was always the biggest concern. nextpnr/yosys don't allow AI PRs so I just keep a fork until they change there mind. Its totally there choice and doesn't affect me in anyway now!
7
239
Deano Calver retweeted
1
4
150
Back in the late 90's we used to send our changed source files to the "Keeper of the Build/Merge Guy" via email, and we shipped a commercial game for Mattel that way.
met a dude at a party last night whose company doesn’t use version control and still writes code ENTIRELY BY HAND. it’s a mysql wrapper. 10million in local healthcare contracts. 1. tech twitter is an insane bubble 2. you actually don’t need anything special to make money
7
4
42
1,337
Deano Calver retweeted
DeepSeek V4.1 Flash 1017 came out yesterday and it already runs on Lucebox. Day zero support for high quality quants. huggingface.co/Lucebox/DeepS…
Our DS4.1 1017 quantizations are already available on day-0, high quality and they can be used on 128GB strix/gorgon halos with only 6GB offloading. Each Lucebox user will have optimized quants in the machine from tomorrow 🚀 huggingface.co/Lucebox/DeepS…
2
4
19
1,804
Even my token usage @bot thinks the new X subscription is bad for me! (SuperGrok Max with free Cursor Ultra) The new plans, called The X Subscription (launched Oct 12), put Cursor, Grok chat and Grok Bot into one shared weekly pool. Claude, GPT and other third-party models stop being included and get billed at API price from prepaid credit. Your legacy Cursor Ultra and SuperGrok Heavy carry on unchanged unless you switch. Switching is permanent, and no deadline has been published. If you swapped both for X Ultra at $200, you'd very likely end up with less total capacity. That's my inference, since the pool sizes aren't public. The only published figure is "at least 2x" the Cursor-model coding usage of old Ultra, and that now has to cover Grok and Bot as well.
170
omg this sh*t is ableist as hell Just wait until nobody cares to send patches to your stupid mailing lists. In a few years, it will cease to be a way to prove a person's competence. Everyone will have their own kernel fork instead. You guys can just entertain yourselves.
11
1
1
71
11,778
Deano Calver retweeted
1/ Today, we're excited to launch PFlash V2. If you ask questions over long documents, retrieved passages or a whole codebase on one GPU, reading the prompt can be most of the wait before the first token. PFlash sits in front of the model and decides which parts of a long prompt the model actually reads. On six public long-context sets it answers 92 of 124 questions against full prefill's 94, while the model reads a median 27% of the prompt, and on one GPU the first token arrives 3.7× sooner on average.
2
4
3
40
5,167
From tabletop to desktop! The complete 1.0 digital adaptation of FROSTHAVEN is OUT NOW on PC ❄️ Now you can get the full experience of the acclaimed board game from Isaac Childres and Cephalofair Games, brought to life by Snapshot Games on Steam & Epic Games Store. Get it today: playfrosthaven.com/
3
12
5
53
3,104
Deano Calver retweeted
Smaller, Smarter, Scalable. Meet #MaixStation, From 27B to 552B, From 3" SoM to 10" miniRack Cluster, Beats DGX Spark. 🎟️Reserve now: sipeed.com/maixstation
82
80
54
477
84,422