The Software Frontier
Subscribe
Sign in
Home
Notes
Chat
Start Here
Archive
About
Latest
Top
Discussions
The Wafer & the Wallet
Memory costs are inflecting up as enterprise token budgets slam shut. The wafer math, the pass-through proof, and the engineering playbook that defends…
Jul 5
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
6
2
June 2026
The Router and the Wire
Mixture-of-experts promised cheaper inference by doing less arithmetic. The bill did not disappear. It moved into the network, and the entire shape of a…
Jun 29
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
8
2
Decode Is Memory-Bound. Speculation Is the Arbitrage
Speculative decoding is the only inference optimization that turns idle silicon into tokens without changing a single output. Whether that lands on your…
Jun 25
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
4
3
The Split and the Seam
Eighteen months ago, splitting prefill from decode was a contrarian research bet. Today it is the default that every serious stack runs, it helped erase…
Jun 21
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
4
1
We wrote the CUDA reference we could not find
The handbook we wanted on our own desks. GPU performance from first principles, current to Blackwell and CUDA 13.x.
Jun 20
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
4
1
The Kill Switch Was in the Mail
How a single Friday letter switched off the world's most capable AI model, turned Anthropic's safety moat into its munition, and marked the second…
Jun 19
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
7
1
4
How three companies set the price of intelligence
HBM, the memory wall, and the physics underneath every token. From the capacitor to the income statement.
Jun 17
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
8
2
The Vertical and the Loop: valuation, compute, and the Anthropic IPO
Anthropic’s confidential trillion-dollar IPO, the three-silicon bet underneath it, the physics of a token, and the circular machine that pays for the…
Jun 10
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
10
2
The Blackwell Migration Question
When you should move Llama 3.3 70B inference from H100 to B200, when you should not, and what the real cost-per-token improvement is once you do.
Jun 7
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
6
2
How Systems Really Fail, Part IV
The complexity problem: why no one designed the system, why no one fully understands it, and why it works anyway.
Jun 3
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
10
1
May 2026
The Llama 3.3 70B Benchmark Problem
What a single H100 SXM5 can and cannot do with Llama 3.3 70B at FP8, a first-principles audit of vLLM, SGLang, and TensorRT-LLM, with the deployment…
May 28
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
8
2
How Systems Really Fail, Part III
The control problem: why the loop you close cannot stabilise the system you have, why every remediation has a half-life, and what it means to act on a…
May 27
•
Lorenzo Bradanini
and
Lorenzo Tettamanti
4
3
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
