Twitter account for the Bosque Development Platform. Tweets by Mark Marron.
Lexington, KY
Joined April 2019
- Tweets325
- Following49
- Followers176
- Likes315
I like using agents to help with coding but I DO NOT like having them run riot through my codebase! Bosque is trying to use syntactic holes to direct where agents write code -- and it feels better.
I also like to try out flows before all the code is complete and holes work for this too -- better than lots of assert(false, "not implemented) statements. A colleague of mine noted that you don't need to actually implement this code. Instead you can dynamically build a table of the right input/output values and use those to simulate the missing bits.
Now you can imagine not "pre-writing" and then running an application but instead, having needed behaviors generated Just-In-Time, at runtime! In fact an AI agent can lazily fill in values, maybe write code, and if the results are not quite what you want, rewind time and try a different branch of what could happen.
We wrote up a short abstract to help us think this through, and will be presenting it at VMIL @VMIL_Workshop (with @splashcon). If the idea of Agenticly-JITed sowtware development sounds check out the abstract and share your thoughts!
arxiv.org/abs/2609.10248
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/
Well Chain-of-Thought (CoT) has been, and perhaps the end of trying to monitor it, has been a topic of conversation today, and honestly, I am happy to say good riddance to this approach!
Trying to read the inner monolouge (if that is even what CoT faithfully represents) and use that information to drive correct behavior is fundamentally a round-about and fragile approach to achieving what we want – a correct outcome.
Rather than trying to accomplish correctness by shaping inner thoughts (or processes) into perfection, we much more robust methods for ensuring desired outcomes. We ask for proof of satisfaction in addition to simply producing an answer or artifact!
More thought on these "proofs-of-satisfaction" is in a short blog post:
bosquelanguage.github.io/202…
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!
Just submitted a proposal to the REBASE industry track at SPLASH @splashcon on trustworthy-by-construction agentic systems -- 2026.splashcon.org/track/spl….
I always enjoy industry/academia cross-over events. Always something interesting to learn.
Y'all should submit too!
Fun feature now usable in Bosque -- ref parameters and variables. They allow simple "locally stateful" style programming while de-sugaring to immutable code.
Instead of manually threading state you can simply "ref" it through and let the compiler handle the book-keeping:
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
Interesting result in the GC and performance space -- porting a simple Raytracer implementation from C# to Bosque and see a 40% to 60% reduction in runtime!
GC behavior is great too! Pauses are rock solid between 14us-60us and nursery overhead is on the order of a few MB over actual heap size!
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
Continuing the topic of reviewing -- I am on the PC for Onward! this year at Splash (@splashcon).
I always enjoy this track -- if you have some big ideas that just haven't come together or interesting thoughts to share it is a great place!
Well I had a lot of fun reviewing for the ACM CAIS Conference @CAISconf (caisconf.org/). I read some really nice papers and think the program looks great.
If you are interested in Agents (who isn't) and want to hear/discuss the leading edge of the field this is a great event to attend!
