Chinny Chukwudozie (@jbernec) header
Chinny Chukwudozie (@jbernec) profile picture
USA
Joined May 2009
Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)Photo by Chinny Chukwudozie (@jbernec)
Chinny Chukwudozie retweeted
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
940
1,200
800
13,277
1,763,918
Chinny Chukwudozie retweeted
Como playing football like this in their first-ever Champions League season 😳 #UCL
229
2,171
115
36,072
2,043,070
Chinny Chukwudozie retweeted
🧵Remember this moment from CNN's town hall with Texas Democrat James Talarico? He told @ErinBurnett and a Texas voter that, at one point when he was a public school teacher, he had 45 students in a classroom. Burnett gushed he was doing "God's work"...
28
189
29
1,963
169,423
Chinny Chukwudozie retweeted
DO YOU REMEMBER AMERICA BEFORE TRUMP?
160
2,207
90
6,124
125,386
Chinny Chukwudozie retweeted
How do you solve the trust problem with AI-generated code? AI agents can generate code at a scale too great for humans to review line-by-line. That makes it difficult to ensure the code will do what the developer intended, and it leaves the final output vulnerable to bugs and security risks. Proof-Driven Development Kit turns plain-language developer intent into a specification in Verus, applying formal methods traditionally used for safety-critical systems. PDD Kit uses mathematical proofs to test agent-generated code against the spec where possible, and clearly indicates where the proofs can’t reach. The result is more reliable agentic code. Researchers @MatthaiP39719 and @alexlavaee break down Proof-Driven Development in the MSR blog: msft.it/6019af2V7
25
30
4
187
19,059
Chinny Chukwudozie retweeted
The church you attend will affect your mental health. Available on all platforms FB | IG | X | TikTok (Abel Damina) YouTube @abeldaminaministries #abeldamina #explore #inChrist #sounddoctrine #christrevealed
12
51
1
123
3,419
Chinny Chukwudozie retweeted
Understanding Fatherhood in the body of Christ. Dr ABEL DAMINA has a special Wisdom when it's comes to Bible interpretation
93
242
24
793
30,072
Chinny Chukwudozie retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence. block.xyz/dessa
4,171
7,149
4,758
69,087
13,714,833
Chinny Chukwudozie retweeted
What’s changed in “the unwritten rules” of engineering management since the 2010s, why are hands-on managers “back”, and what has it done to the engineer-to-CTO career path? With Will Larson (@Lethain). Timestamps: 00:00 Intro 08:20 Stories from Yahoo! 12:47 Digg’s v4 rewrite: the insider story 26:02 Will’s path to eng leadership 30:03 Uber, Stripe, Carta, and Calm 35:11 What does a CTO do? 38:09 Will’s role at Imprint 42:48 How engineering management has evolved 51:08 ZIRP’s impact on tech 57:21 Career ladders 1:01:03 Eng 1 vs Eng 2 1:06:58 How software engineering roles are changing 1:16:25 Revised rules of engineering leadership 1:21:57 The risks of becoming a bureaucrat as an EM 1:25:57 How to become a CTO? 1:31:33 Middle management vs. line management 1:41:36 Will’s writing 1:52:13 Book recommendations Brought to you by: • @turbopuffer – vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable. turbopuffer.com/v3 • @EntireHQ – Git hosting, rebuilt for the agentic era. Entire hosts your code in-region, and is up to 89x faster than any other competitor. entire.io/pragmatic • What if you only needed a single test to harden your system? Get a free introduction to property-based testing: through a live, online webinar hosted by Hillel Wayne, author of Logic for Programmers and Developer Educator at @AntithesisHQ. RSVP here: pages.antithesis.com/webinar… Two sage observations from Will on how engineering management changed: 1. ZIRP shaped engineering management practices in the 2010s, Will believes. As he put it: “Back then, your ability to hire and close and retain became the differentiator between successful companies. The less successful ones simply couldn’t retain great people. [This dynamic on hiring and retaining] pulled leverage back into the engineer’s hands and created a very different environment. So, companies were pitching themselves as a more relaxed environment, more focused on you, and offering more career development. And I think in ways that I think were often kind of self-defeating.” 2. Blunt message for middle managers: retire or re-skill. Will left a team of 250 at Carta to head up 25 tech people at Imprint. He purposely took a “step back” in his leadership career because he believes things are changing so radically that the engineering leadership profession that we know will not exist in three years. Amid all this, Will says that line management can be a lot more engaging for executives these days because the tools for line management and the tools for writing software are really good. Plus, the tech industry has always been volatile: during the 2010s most of us simply forgot about this!
15
23
7
161
38,191
Chinny Chukwudozie retweeted
Lamine Yamal from that angle?! 🫨 #UCL
203
2,894
113
54,176
2,009,384
Chinny Chukwudozie retweeted
I've never trusted code I didn't review until now. Agents write more code than any of us can review. We often end up skimming the PR/diff and pushing. Current review methods do not prove the code is correct or does what we asked. Recent research found the best AI code reviewer caught the bug on its first try only 42% of the time.* The evaluation bottleneck, regressions, and security incidents have forced us to find a better way. Introducing Proof-Driven Development Kit (PDD Kit) from @MSFTResearch. PDD Kit brings assurance to AI-generated code. You describe what you want to build in plain English. PDD Kit captures your objective, what we call your intent, and uses a verifier tool to prove the code meets it for every possible input. You never review a single line of the code or the proof. You review your plan and the defined objectives in natural language. A simple example is login. With testing, you check that only the correct password logs in a user but with a proof on top you can verify that there is no case a wrong password allows login. You can prove correctness and security across many complex scenarios. Not only does PDD Kit prove the correctness of your code, but also your intent so you can have confidence your code is correct and does what you asked. It provides a level of assurance that specs, code review, and tests never could. PDD Kit is in limited research preview. Video explainer below. If you want to learn more, I'll be sharing PDD Kit at GitHub Universe next week, Oct 28–29. Swing by the Speakeasy, ask for GitHub Next, and ask me about verified code. If you're in SF, let me know. *Yang et al., "(When) Should a Software Factory be Lights-off?", Microsoft Research and CMU, Oct 2026
How do you _guarantee_ your agent's code is correct? You prove it. Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch. PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team. PDD Kit takes an app's login flow from intent to a verified pull request: It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust. Once you approve the spec, the Verus verifier automatically proves the code meets it. Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs). It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible. The goal is a verified software factory, where engineers review specifications instead of code. Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
50
59
6
1,138
165,511
Chinny Chukwudozie retweeted
How do you _guarantee_ your agent's code is correct? You prove it. Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch. PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team. PDD Kit takes an app's login flow from intent to a verified pull request: It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust. Once you approve the spec, the Verus verifier automatically proves the code meets it. Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs). It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible. The goal is a verified software factory, where engineers review specifications instead of code. Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
86
134
78
2,059
398,357
Chinny Chukwudozie retweeted
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
2,427
4,267
4,778
55,566
11,686,075
Chinny Chukwudozie retweeted
Hi, I'm Felix. I'm an eng lead working on Claude. I love watching people take flight and do things they never thought possible. We often describe that as "being more ambitious" when using AI, which is tricky advice to follow. I wrote a tutorial: felixrieseberg.com/how-to-be…
414
2,607
610
24,625
5,507,069
Chinny Chukwudozie retweeted
Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.
275
353
334
6,329
984,228
Chinny Chukwudozie retweeted
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side. It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
988
917
786
20,849
2,386,952
Chinny Chukwudozie retweeted
New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
1,174
2,662
2,203
25,964
8,362,035
Chinny Chukwudozie retweeted
Two special Lamine Yamal assists 😮‍💨 Who did it best here? 🅰️ @lays_football | #UCLassists
🤝 Paid partnership
367
5,763
276
76,917
2,601,506
Chinny Chukwudozie retweeted
Galatasaray 1️⃣-4️⃣ FC Barcelona
332
3,021
177
41,706
1,503,413