Who's Who of AI

Matthew Green

92 trust @matthewdgreen.bsky.social · 18,614 followers @matthew_d_green · 0 followers
Why they matter

Tracked through public AI activity and peer connections inside the directory.

AI signals
2
past 30d
Sources
2
distinct domains
Discussions
2
past 30d
Latest signal
16d ago
View every signal from Matthew Green →
I teach cryptography at Johns Hopkins. https://blog.cryptographyengineering.com
What they're sharing

Articles & links

@Nairebis @perrymetzger We are starting to find emergent mechanisms that at least superficially resemble this. I don’t claim their consciousness. But you could imagine something like this becoming an element of consciousness in a larger persistent model. https://t.co/w3G827cdJX

A global workspace in language models \ Anthropic anthropic.com
AI Weekly's analysis →
  • Anthropic says Claude has a 'J-space' of dozens of concepts, under a tenth of neural activity, that mediates multi-step reasoning.
  • Swapping 'spider' for 'ant' inside the J-space changed Claude's leg-count answer from 8 to 6, demonstrating a causal role.
  • A 'J-lens' tool surfaced silent words like 'fake', 'fictional' and 'manipulation' during deception tests, pointing at safety uses.
Read full analysis →
View on Bluesky · ♥ 0 ↻ 0 ↩ 0 · 10 from the directory shared this · 16d ago

I’ve been working on a hobby project to crack classical ciphers. The guts of it is to see whether frontier LLMs, given the right tools, can do a good job cracking a broad range of historical ciphers. github.com/matthewdgree...

GitHub - matthewdgreen/decipher: An AI-enabled application for cracking ciphers github.com
AI Weekly's analysis →
  • Cryptographer Matthew D. Green released Decipher, an open-source toolkit that cracks classical ciphers via CLI, an MCP server, or an agentic LLM loop.
  • The toolkit bundles Rust-accelerated simulated annealing solvers covering substitution, Vigenère, Quagmire, transposition and composite pipelines under GPLv3.
  • Its README explicitly instructs AI agents not to fetch or build external frameworks like cDecryptor, AZdecrypt or zkdecrypto during tasks.
Read full analysis →
View on Bluesky · ♥ 87 ↻ 18 ↩ 5 · 2 from the directory shared this · 92d ago
Their own posts

Recent commentary

Me: makes silly offhand comment about AI and public key cryptanalysis. People freak out. Also me: does a serious analysis of cryptanalytic effort so far set against recent LLM math results, which is (IMHO) wildly more terrifying. Nobody notices.

View on Bluesky · ♥ 78 ↻ 10 ↩ 4 · 9d ago

So I told GPT-6 to make me a virtualized simulation of a water treatment plant and now I’m spending a lot of time saying “please document that this is just for defensive purposes” because I realize how bad it looks.

View on Bluesky · ♥ 46 ↻ 2 ↩ 4 · 36d ago

I would be interested in an actual discussion of AI consciousness that isn’t just assertions, or facile arguments about current models having limited memories. (We don’t treat amnesiacs as lacking consciousness.)

View on Bluesky · ♥ 25 ↻ 1 ↩ 9 · 17d ago
Their network

In Matthew Green's orbit

Center = Matthew Green. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.

Are you Matthew Green? Show it.

Add the Who’s Who of AI badge to your site or bio. It links back to this profile.

Listed in AI Weekly's Who's Who of AI

Markdown: [![Listed in AI Weekly's Who's Who of AI](https://aiweekly.co/modules/custom/aiweekly_whoswho/images/whoswho-badge.svg)](https://aiweekly.co/whos-who/person/matthewdgreen-bsky-social)