I added multiplayer and told codex to shut up, and it was smart enough to understand the situation. xD
LLMS
-
Cloud codex runner using Cloudflare Firecracker and Ghostty
By
–
Still limited by compute, so I built a thing that runs codex in the cloud, powered by @Cloudflare firecracker boxes (and since that's not beefy enough for larger projects, tests are run via crabbox) Uses Ghostty ofc, via WebAssembly.
Codex replicated itself, basically. -
ConvexTok: Linear Programming for Optimal LLM Tokenization
By
–
"Tokenisation via Convex Relaxations" Most LLM tokenizers still use BPE, a greedy merge algorithm that can waste vocab slots on locally good but globally suboptimal tokens. This paper turns tokenizer training into a linear program, then rounds the solution into ConvexTok. This
-
Codex for building and debugging iPhone simulator end to end
By
–
Codex for building and debugging an iPhone simulator end to end: https://t.co/qA5WlK0OzA
— Greg Brockman (@gdb) 23 mai 2026Codex for building and debugging an iPhone simulator end to end:
-
Opus 4.8 found in Google Vertex, Sonnet 4.8 leak confirmed
By
–
Can found opus 4.8 in Google Vertex. Can’t confirm any of this tho. However, the fact that Sonnet 4.8 is coming soon has been common knowledge since the data leak. The inclusion of Opus 4.8 in Vertex comes as a surprise to me – though, considering the accelerated release
-
ConvexTok vs BPE: moving tokenization toward optimality
By
–
The key distinction: BPE gives us a strong procedure. ConvexTok gives us a procedure, an optimization relaxation, and a certificate. That moves tokenisation from engineering folklore toward measurable optimality.
-
Paper: Tokenisation via Convex Relaxations reframes tokenizers
By
–
The tokenizer is an architectural prior disguised as preprocessing. And almost everyone has been treating it like plumbing. A new paper by Jan Tempus, Philip Whittington, Craig W. Schmidt, Dennis Komm, and Tiago Pimentel changes the frame: Tokenisation via Convex Relaxations
-
LLM vs RAG vs AI Agent vs MCP Comparison
By
–
#LLM vs. RAG vs. #AIAgent vs. MCP
by @Python_Dv #GenerativeAI #ArtificialIntelligence #MachineLearning #ML -
Tokenization as Architectural Prior: New Research Paper
By
–
The tokenizer is an architectural prior disguised as preprocessing. And almost everyone has been treating it like plumbing. A new paper by Jan Tempus, Philip Whittington, Craig W. Schmidt, Dennis Komm, and Tiago Pimentel changes the frame: Tokenisation via Convex Relaxations
-
Anthropic’s Powerful Cybersecurity AI Model Shared Selectively After Revealing 10,000+ Vulnerabilities
By
–
Anthropic created a cybersecurity model so dangerous that it decided not to release it to the public. Instead, it gave it to companies like Apple, Google, Microsoft, AWS, and Cloudflare. And in just one month:
→ 10,000+ vulnerabilities found
→ bugs hidden for 27 years