Macroscope @Macroscope

Command your own software factory. macroscope.com San Francisco Joined March 2025

Tweets

192
Followers

1K
Following

30
Likes

257

Macroscope @Macroscope

4 hours ago

@FireworksAI_HQ @Rob_Bishop 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/macroscop…

0 0 0 14 0

View Details

Macroscope @Macroscope

4 hours ago

@FireworksAI_HQ @Rob_Bishop Register here: fireworks.ai/event/build-li…

0 0 0 24 0

View Details

Macroscope @Macroscope

4 hours ago

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 1 4 7K 3

View Details

Macroscope @Macroscope

2 days ago

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

0 0 0 88 0

View Details

Macroscope @Macroscope

2 days ago

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 0 1 131 0

View Details

Macroscope @Macroscope

2 days ago

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 0 1 126 0

View Details

Macroscope @Macroscope

2 days ago

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 0 3 174 0

View Details

Macroscope @Macroscope

2 days ago

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 15 4K 7

View Details

Macroscope @Macroscope

3 days ago

Learn more about how we built MacroscopeBench and how it works here: macroscope.com/blog/macroscop…

0 2 6 423 0

View Details

Macroscope @Macroscope

3 days ago

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 0 4 127 1

View Details

Macroscope @Macroscope

3 days ago

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-in…

1 7 14 57K 2

View Details

Macroscope @Macroscope

2 weeks ago

We're hosting our first webinar on 9/22! Ivan from Macroscope team is walking through the four things Macroscope code review actually does to a pull request: review, gate, approve, & report. We'll show you how to use AI code review tools to get a PR from open to merged without a human in the loop. Register below 👇 luma.com/1fw8z3lt

0 1 10 602 5

View Details

Macroscope @Macroscope

2 weeks ago

@Pze_pos @theo @Pze_pos 👋 so sorry you ran into this, this is a billing issue on our end due to a previous sign up and usage. We've added $100 dollars to your account for the inconvenience, you're all good to go now! Thanks for giving us a try!

1 0 1 92 0

View Details

Macroscope @Macroscope

2 weeks ago

@Pze_pos @theo team is looking into this 🔍

1 0 1 83 0

View Details

Macroscope @Macroscope

2 weeks ago

@matt_chisolm Thank you 💙

0 0 1 7 0

View Details

Macroscope @Macroscope

2 weeks ago

Will you run your Murmur agents on an iPhone Duo?

1 2 10 903 1

View Details

Lightspeed @lightspeedvp

2 weeks ago

“A single engineer might be capable of directing dozens of productive agents, yet in practice can only keep a handful moving at once.” Exciting early preview from @kayvz and the @Macroscope team, making it easier for engineers to direct fleets of coding agents in the cloud and for work to stay in motion.