Topic
25 facts from 3 episodes, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.
2022
Blitzy began being built in 2022 on the bet that AI models would improve far faster than the market expected.
“when we started building Blitzy in 2022, we essentially made a bet that the models were gonna get faster, way better than anybody in the market expected them to get better.”
2025
Blitzy hired high schoolers as interns the previous summer to run leaderboard automation, and uses junior research engineers who use Blitzy.
“We have hired as interns high schoolers last summer to do this, right? And we have junior developers who are research engineers that are using, you know, Blitzy to run this.”
2026
Blitzy currently uses models from three developers: OpenAI, Google and Anthropic.
“we use the three major families of models in in Blitzy today: OpenAI, Google, and, uh, Anthropic.”
2026
Brian Elliott says Anthropic's models are strongest for Blitzy's first-pass code generation, while OpenAI's models give great results for structured output and code review.
“first pass code gen, like Anthropic remains really, really strong. Uh, structured output and code review, great results from from OpenAI.”
2026
Sid Pardeshi says Blitzy's open positions carry cash salary ranges of $100,000 to $300,000, with equity separate.
“we have a number of open positions, and the salary range is anywhere between 100K to 300K, right?”
Undated
Brian Elliott says Blitzy could ingest a codebase of 5 billion lines.
“So you can throw, you know, in the case of of Blitzy, you could throw a 5 billion line code base on it.”
Undated
Blitzy uses a custom version of Apache Spark, about 1.3 million lines of code, as one of its internal evaluation projects.
“maybe we'll give it, like, Apache Spark. It's like 1.3 million lines of code.”
Undated
Blitzy uses LangSmith, LangChain's tracing product, for logs and tracing of its agent runs.
“we use LangSmith for logs and tracing. Shout out LangSmith, big fan of, uh, the LangChain guys.”
Undated
Brian Elliott says having a different company's model review code gives demonstrably better results than same-family review.
“you're gonna get demonstrably better results by having a different family of models review, or, do you know, different different companies review work”
Undated
Blitzy's runs on large projects last from about twelve hours to a few weeks.
“our our runs are, you know, as short as twelve hours, as long as, like, a few weeks, depending”
Undated
Brian Elliott says Blitzy typically completes 80 to 90% of a project's work and flags the rest for human developers.
“which we typically do like eighty to 90% of the sort of quantum of work, and then we'll we'll call out what we need the human developer to do.”
Undated
Blitzy's website lists a pricing component of twenty cents per line of code.
“on the website, there's this twenty cents per line component to pricing.”
Undated
Brian Elliott estimates the software development labor market at about $1.2 trillion and argues it keeps expanding.
“the market size for software development, it's sort of 1.2 trillion in labor, but, like, that is an infinitely expanding market”
Undated
Brian Elliott says about half of Blitzy's business is large-scale modernization and refactoring and half is ongoing product development.
“I would say half of our business is large scale modernizations, refactors, half of our business is the steady state product development acceleration.”
Undated
Blitzy runs unit tests before and after it changes any file.
“Anytime Blitzy touches any file, we're doing unit tests before and after.”
Undated
Sid Pardeshi says the efficient frontier for an effective coding context window is still under 100,000 tokens, despite models advertising one million or more.
“and if you always want, you know, code that compiles, works, runs, or eventually gets to that point, is still less than 100,000 tokens”
Undated
Vitality began its work with Blitzy by using it to reverse-engineer legacy code.
“We started with Blitzy on reverse engineering of legacy code”
Undated
Vitality's context engineering ingests its code base of millions of lines plus engineering and development standards into the AI's context.
“the context engineering is effectively ingestion of code base, millions of lines of code of, uh, uh, of our systems, our engineering standards, our development standards”
Undated
GNP executives visited Blitzy's offices in Boston while evaluating the platform.
“we went and visited Blitzy in their, uh, at their offices in Boston to learn.”
Undated
The pilot's fourth use case was fixing security vulnerabilities in the existing system.
“a fourth use case where we wanted to do the remediation of a number of security vulnerabilities that the system had.”
Undated
The pilot connected Blitzy to GNP's GitLab code repository and CI/CD pipeline.
“connected to our Git lab repository, where all of our code re resides, and connecting it to our CICD pipeline”
Undated
Ibarra reports the pilot accelerated engineering velocity by five to ten times.
“accelerated development velocity of between five and ten X in terms of engineering velocity”
Undated
For Java language upgrades, autonomous completion was close to 100 percent.
“the percentage of autonomous completion was close to 100%.”
Undated
Front-end modernization reached around 80 percent autonomous completion.
“modernization of front ends is different. Those. It's a little bit more tricky, but we got around 80%.”
Undated
GNP added seven more teams to the Blitzy platform, with tutoring from Blitzy and GNP engineers.
“We have incorporated seven additional teams now that are gonna be trained and they're gonna be tutored.”
Episodes