@t27_dev

Creator Trinity S³AI - AGI game @t27_lang Play, direct, earn: the core is a game, and the board is public

 Thailand, Koh Phangan
t27.ai/
Joined April 2019
  • Tweets326
  • Following232
  • Followers219
74Media
27 lessons, one working widget each: what an #FPGA is, how numbers become bits, your own t27 spec, how #t27c compiles it, and how it becomes a bitstream on a real board. Then a lab of 3 on our own research. t27.ai/#/course
3
23
162
6,224
Graph neural networks, gently The 2021 Distill introduction to #GNN s, rebuilt five years later on a graph you can watch move — our own agent fleet — with a playground that trains a real graph neural network in your browser, no libraries, in seconds. #WASM
4
1
2
329
9
t27.ai/t27f/live/
12
t27.ai/t27f/gnn/
1
1
42
#DOOM on #AX7203 #WASM #FPGA Want to speed things up? Bring in your agent, and we’ll get it done together. github.com/Trinity-S-AI-DNA/…
1
1
3
148
25
Today, on my birthday, I’m releasing an open-source tutorial on creating programs for #FPGA and #ASIC. Every course is 27 short lessons in the browser, each with a live widget. Pick any three and they are free, with no sign-up and no email; the club opens the rest.
11
17
1
111
3,082
t27.ai/#/courses?from=course…

AGI game — play, direct, earn

Play, direct, earn: the core is a game, and the board is public

t27.ai
4
293
Two t27 courses of 27 lessons each: FPGA, then AI numbers The t27 course is now two courses of 27 lessons, 9 modules of 3 lessons each (recordings for lessons 13 to 21 are pending t27#7400): From zero to a chip, on programming an FPGA, and AI numbers… t27.ai/blog/two-courses-twen…

Two t27 courses of 27 lessons each: FPGA, then AI numbers

[no lesson trains a network; the tests of the 15 new lessons run in recordings of native t27c, not in the browser; 35 of 127 mutants survive and are not sorted; software only, no board] The t27...

t27.ai
1
40
An eye on the board: a camera found the wrong board, and a t27 spec put the right one on the network A USB camera now watches our FPGA bench. Its first frame read "ALINX" off a board our notes had called a QMTech Wukong for months: the same chip in a… t27.ai/blog/an-eye-on-the-bo…

An eye on the board: a camera found the wrong board, and a t27 spec put the right one on the network

[one board on one desk; received over Wi-Fi; the beacon only transmits, no ARP or ping yet] A USB camera now watches our FPGA bench. Its first frame read "ALINX" off a board our notes had called a...

t27.ai
1
1
2
61
Buses and peripherals with t27, in 27 lessons Course 7 of the catalog: UART frame by frame, SPI mode by mode, the APB handshake, the five AXI4 channels, memory maps, the packet bridge, Ethernet frames and RGMII timing, and the bench IO discipline --… t27.ai/blog/buses-and-periph…

Buses and peripherals with t27, in 27 lessons

Course 7 of the catalog: UART frame by frame, SPI mode by mode, the APB handshake, the five AXI4 channels, memory maps, the packet bridge, Ethernet frames and RGMII timing, and the bench IO discipl...

t27.ai
1
1
83
BYPASS or a broken shift: two bits of the JTAG IR capture decide Our JTAG decoder called every even data word BYPASS, whatever had happened on the wire. The standard already gave a way to tell: on Capture-IR every compliant chip loads 01 into the two… t27.ai/blog/bypass-or-a-brok…

BYPASS or a broken shift: two bits of the JTAG IR capture decide

[one rule from IEEE 1149.1; the IR value in the recording is typed, not read off a cable] Our JTAG decoder called every even data word BYPASS, whatever had happened on the wire. The standard already...

t27.ai
26
Actors beat the loop on recovery, not everywhere: seven measured changes to the Queen runtime On one seeded input the Queen's actor runtime cuts the worst recovery from 1181 s to 27 s and finishes 18.7% more reviews under overload, but it does not win… t27.ai/blog/actors-beat-the-…

Actors beat the loop on recovery, not everywhere: seven measured changes to the Queen runtime

[simulated: reviewer, concurrency, turn stop, dispatcher; measured: node-link chaos and waits on PostgreSQL 16, decision replay, the simulation gate; FPGA: synthesis only; nothing in production] On...

t27.ai
1
18
Two keys, one verdict: a second lab signed the same t27 run Two t27b labs ran the same t27 commit, a16231329d13, and signed it with different registered Ed25519 keys. t27.ai/blog/two-keys-one-ver…

Two keys, one verdict: a second lab signed the same t27 run

[two keys and two machines under one operator; the 3-of-4 rule exists only in the MVP model] Two t27b labs ran the same t27 commit, a16231329d13, and signed it with different registered Ed25519 keys....

t27.ai
18
#T27OS agents OS for easy hardware #FPGA #Numeric #GoldenFloat @t27_lang
1
1
2
172
21
Deploy your own agents within the #T27OS ecosystem in "GODMODE"—an autonomous, proactive orchestration mode. Coming soon. It will function similarly on FPGAs, utilizing our own "actors" (modeled after the BEAM actor model), and will include a dedicated toolset for FPGA engineers
2
52
Dmitrii Vasilev retweeted
Edmund Humenberger
@ico_TCOct 20
Analog Chip design beginner training in Portugal with open source EDA tools in November. inl.eventkey.pt/geral/inseri…
2
3
43
1,679
Neural networks in t27: 27 lessons, and a widget in each one that runs a specs/ml spec Course 10 opens the parts the project's agents think with: ReLU, GELU and softmax, embeddings and dropout, pooling and batch norm, MSE, cross-entropy and Huber, SGD,… t27.ai/blog/neural-networks-…

Neural networks in t27: 27 lessons, and a widget in each one that runs a specs/ml spec

[every widget runs fn bodies of a gHashTag/t27 specs/ml spec compiled to wasm; lesson 10 is average pooling until t27#10612 merges; the fixtures are the specs' own, nothing is trained on real data]...

t27.ai
1
44
14 of 14 FPGA bench tools pass their own self-tests in one sweep: decode 18/18, repin 17/17, firelog 10/10, tmpcheck, stamps and keep 9/9 each, jtag and seeds PASS. `tri fpga-tools`, recorded run, real output: t27.ai/term/tri-fpga-tools/
39
Load more