@Macroscope

Command your own software factory.

 San Francisco
macroscope.com
Joined March 2025
  • Tweets205
  • Following32
  • Followers1.3K
64Media
Today we are introducing Murmur, our cloud agent orchestration system. Here's an early preview of Murmur:
Kayvon Beykpour
@kayvzSep 3

Introducing Murmur

Article · @kayvz
3
6
12
13,111
Back for day 2 of ELC! Loved all the conversations yesterday and are excited for more today. If you’re at the conference, come say hi :)
2
1
10
307
Yesterday's #SFTechWeek Clickety Clack Café, in photos 📷 Thanks for stopping by! And if your PR needs another shot, check out Macroscope: macroscope.com
1
7
369
PSA: free coffee and matcha at 500 Folsom St until 4:30pm 🍵 Grab a hot (or cold) fix before your next #SFTechWeek event. We'll be here (caffeinated).
3
9
766
Clickety Clack Café is live!☕️ Coffee & code review on Macroscope. Register for location: partiful.com/e/1XFyBiTbjMeIm… #SFTechWeek
1
2
8
441
Macroscope retweeted
Lightfield
@lightfldOct 6
Replying to @Macroscope
@Macroscope runs its go-to-market on a business world model built with Lightfield. They ingest customer touchpoints across marketing interactions, product use, and sales into a single platform. This gives agents full context on entire customer lifecycle. Agentic workflows that used to take months to build in other systems can be designed in hours using natural language. Read how Macroscope is building its GTM system. lightfield.app/customers/mac…
2
1
8
881
Tomorrow: free coffee for everyone at #SFTechWeek. Clickety Clack Café, 1:30 to 4:30pm. RSVP for the location. Coffee & Code review on us. partiful.com/e/1XFyBiTbjMeIm…
2
2
11
780
Macroscope retweeted
Macroscope
@MacroscopeOct 1
Replying to @cars24india
@cars24india is one of India's largest auto-tech companies: 300M+ users, $1B+ in revenue, 400 engineers. with Macroscope, they saw up to 3x more code reaching production in 3 months. 🧵
4
4
14
501
🥉 GPT 6.1 Sol debuts at #3 on our code review leaderboard. It comes below GPT 6 Sol because recall is lower, but it leaves 30% fewer comments with very high precision. It also slightly beats workhorse Astra at a seventh of the price! See full results: macroscope.com/benchmark
3
3
15
5,272
We're opening a coffee cart for #SFTechWeek ☕ Free coffee and matcha for everyone shipping code Tue Oct 6, 1:30 to 4:30pm, downtown SF. RSVP for location drop. partiful.com/e/1XFyBiTbjMeIm…
4
8
1
21
4,094
Building on the release of MacroscopeBench, we’ve been researching post-training our own models at Macroscope, leveraging training infrastructure from @FireworksAI_HQ . Our co-founder, @Rob_Bishop, and Vivek Chauhan, product lead for training at Fireworks, will be sharing learnings from the collaboration on Sep 29, 11am PT.
2
3
7
71,927
As a reminder: Macroscope never trains on customer data. Both MacroscopeBench and our model-training datasets are built from real bugs in open-source repositories. Learn more about our methodology: macroscope.com/blog/macrosco…

MacroscopeBench: A real-world benchmark for evaluating code review

How we built MacroscopeBench: 12,000+ validated real bugs from 1,500+ open source repositories across 14 languages, and how we score recall, precision, cost and latency.

macroscope.com
43
Replying to @Macroscope @FireworksAI_HQ @Rob_Bishop
Register here: fireworks.ai/event/build-lik…

Build Like a Frontier Lab: Macroscope | Fireworks

In this webinar, Rob Bishop, Co-founder of Macroscope, shares how his team decided to train its own code-review model after finding that existing models couldn’t deliver the right combination of...

fireworks.ai
1
128
GPT-6 Sol scored 80.3, #2 overall, behind only Claude Opus 5.5 max. It is ahead of GPT-6 Astra at less than half Astra's cost. Against GPT-5.6 Sol it matches the old model's best score at half the price
1
1
143
GPT-6 Luna, while ranking at #13 using max effort, still delivers great performance for extremely low prices. It reached 93% of GPT-6 Astra's score for about 1/60th of the cost! It holds a very respectable f1 score due to its very high precision (89.1%), second only to Astra
90
There are some new top models leading our code review benchmark. 🥇 Claude Opus 5.5 — 82.3 (f1 score) 🥈 GPT-6 Sol — 80.3 🥉 GPT-6 Astra — 78.0 See full results here: macroscope.com/benchmark
4
6
2
15
4,073
more replies
Compared to Opus 5, Opus 5.5 is better, cheaper and faster at every effort level, usually around 1/5th of the cost and up to 4x faster
1
1
151
Claude Opus 5.5 at max effort takes #1 with impressive recall (80.6%) and precision (84%). The downside: cost and latency, being the most expensive model we’ve tested xHigh effort level still delivers very strong performance, very similar to GPT 6 Sol max at half the latency.
1
4
218
Production is the worst place to find out if your code reviewer is good enough MacroscopeBench measures it first, against real bugs that shipped, just not in your repo. It is now the only trusted benchmark for code review on @FireworksAI_HQ SII Index fireworks.ai/specialized-int…
1
7
1
13
81,170
we rewind to the commit that introduced each bug and ask whether a reviewer would have caught it there. it's never told a bug exists. see which models currently perform the best at macroscope.com/benchmark
1
4
164
Learn more about how we built MacroscopeBench and how it works here: macroscope.com/blog/macrosco…
2
1
7
430
Load more