Twitter account for the Bosque Development Platform. Tweets by Mark Marron.
Lexington, KY
Joined April 2019
- Tweets329
- Following49
- Followers172
- Likes330
BosqueLanguage retweeted
Delighted to share the the work of my team at
@GoogleDeepMind: formally verifying a real-world implementation of the #Signal cryptographic protocol at the machine-code level. The proof was done using AlphaProof Code, our new AI framework for formal specification and verification.
Our teams put Gemini 4 Carbon to work on a major security challenge: mathematically proving the code underlying the Signal protocol.
Using AlphaProof Code, @GoogleDeepMind researchers guided agents to verify the protocol down to compiled device code, closing the gap where real bugs hide. The result:
- Gemini 4 Carbon generated over 6M lines of machine-checked Lean proofs
- years of expert manual verification compressed to just weeks
~1% of the codebase required human review (Lean automatically checked the rest)
This is helping unlock scalable formal verification for building secure software, laying the groundwork to fundamentally shift the advantage to defenders. We’re open sourcing the results for the security community.
BosqueLanguage retweeted
Beam’s model technical report is now available. Read the full report to learn about the methodology our team used to train Beam end-to-end in-house, here: reflection.ai/documents/beam…
BosqueLanguage retweeted
AI oversight and control is the most difficult problem I can think of. Come help me try to solve it
We're hiring! Come help us build tools for overseeing powerful AIs oath.tech/jobs/
BosqueLanguage retweeted
We're hiring! Come help us build tools for overseeing powerful AIs oath.tech/jobs/
BosqueLanguage retweeted
Are you working on language implementations and implementation research?
Do you want to present your work to an enthusiastic crowed in Oakland?
Submit your work to the @VMIL_Workshop!
BosqueLanguage retweeted
For the past few months I've been building SafeRE, a production-grade, linear-time regex engine for Java, using agents.
I started a blog series about it: eaftan.github.io/safere-intr…
Code: github.com/eaftan/safere
I’d love feedback from anyone trying it, especially in production.
BosqueLanguage retweeted
📢 REBASE 2026 (@splashcon, @issta_conf) is looking for speakers!
We want to hear from practitioners & researchers in PL, dev tools, software engineering, security, and AI for code.
Check out the CfP: 2026.splashcon.org/track/spl…
#SPLASH2026 #ISSTA26 #OOPSLA #SoftwareEngineering
BosqueLanguage retweeted
New post: Local Reasoning for Global Properties. Could programming language design come to the rescue?
BosqueLanguage retweeted
AI agents don't succeed on model quality alone. They succeed when they're grounded in the context of the business: data, workflows, policies, and shared knowledge.
Join me and @amrcn_werewolf at #MSBuild tomorrow to see how Microsoft IQ turns enterprise context into action—helping agents reason, decide, and deliver real outcomes.
aka.ms/build2026-brk240
#AI #Agents
BosqueLanguage retweeted
My paper with @ReshabhSharma01 and @shraddha_96, “Willful Disobedience: Automatically Detecting Failures in Agentic Traces”, will appear this month in the First ACM Conference on AI and Agentic Systems (CAIS 2026). arxiv.org/abs/2603.23806
BosqueLanguage retweeted
The Static Analysis Symposium (SAS) is taking place as a part of SPLASH/ISSTA this year! Consider submitting a paper, deadline *May 1st*, with special topics including Static Analysis and AI, and Static Analysis and Education:
conf.researchr.org/home/spla…
BosqueLanguage retweeted
Feedback loops are shaped as Counter-example Guided Inductive Synthesis.
Two dueling players: coding agent proposes, oracle finds a counterexample, repeat until specification and implementation converge.
BosqueLanguage retweeted
AI is writing a growing share of the world's software. No one is formally verifying any of it.
New essay: "When AI Writes the World's Software, Who Verifies It?"
leodemoura.github.io/blog/20…
BosqueLanguage retweeted
Agree that it's very interesting for PL+formal methods.
(i) for PL, the source and object code, and mapping between them, are all up for grabs
(ii) for formal methods, proving is becoming less of a blocker, and control over codegen means codegen can be optimized for provability (like Hoare and Dijkstra advocated for).
I think it must be a very interesting time to be in programming languages and formal methods because LLMs change the whole constraints landscape of software completely. Hints of this can already be seen, e.g. in the rising momentum behind porting C to Rust or the growing interest in upgrading legacy code bases in COBOL or etc. In particular, LLMs are *especially* good at translation compared to de-novo generation because 1) the original code base acts as a kind of highly detailed prompt, and 2) as a reference to write concrete tests with respect to. That said, even Rust is nowhere near optimal for LLMs as a target language. What kind of language is optimal? What concessions (if any) are still carved out for humans? Incredibly interesting new questions and opportunities. It feels likely that we'll end up re-writing large fractions of all software ever written many times over.
BosqueLanguage retweeted
I wrote an essay on proof assistants in the age of AI.
leodemoura.github.io/blog/20…
BosqueLanguage retweeted
"Readable formal specifications are not a convenience that AI can replace. They are the foundation of trust."
twp.ai/4iwRw1
