Intent Computing (@intentprover) header
Intent Computing (@intentprover) profile picture

Verify code against your intent.

San Francisco, CA
Joined November 2026
Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)Photo by Intent Computing (@intentprover)
benchmarks get interesting in the footnotes.
1
16
somewhere in your codebase, “obviously” is doing the work of a proof.
2
76
“you know what i mean” is a bold thing to tell a computer.
3
131
we went from room-sized computers to code written in seconds. “should work” has had a suspiciously long career.
3
27
your agent has finished the task. please allow 3 to 5 business days to find out what it did.
3
43
the internet has receipts. We’ve been collecting them in Stack State: > reported software failures > published proofs and the sources behind both.
1
1
8
119
Attack tracks reported incidents linked to flaws in code. what failed? who was hit? and the reported impact. Defense maps published formal verification (which components have proofs, who did the work, and what those proofs cover).
1
3
40
Open the map. Look up something you use. Tell us what you’d want proved about it. If there’s already a proof we missed, send the paper or repo. stackstate.ai/
2
7
We froze Redis for 40 seconds with 23 characters. All we searched was a one-item array. A PING from another client didn’t get a reply until the search finished.
1
4
119
The PR author ran the same pattern on two Redis builds on an Apple M3. Original: 20.338 s to finish. Proposed patch: 0.071 ms to reject it. Both builds returned identical replies on 76 cases within the new limit. github.com/redis/redis/pull/…
1
1
19
The proposed patch estimates how big the regex will get when its repeats expand. If the estimate exceeds 10,000 nodes, Redis rejects the pattern before doing that work.
1
5
i said i’d take a quick look
1
1
5
76
We want to give agents bigger jobs without creating bigger review queues. If a payment request is retried, the customer should only be charged once. We should be able to verify that directly without reading the whole diff.
3
26
we doubled the score on an OpenAI benchmark task. 0 models trained. 0 predictions moved in the ranking. benchmark speedrun any%
1
5
57
The Jigsaw grader turned predictions into 0s and 1s before scoring them. Multiply all 400 predictions by 0.49 and the grader sees 400 zeros. We removed that one line locally. Both versions scored 1.00.
1
3
34
fired before its first day. the software tried to shut down a machine it had never created.
1
4
44
Ray’s autoscaler reused one mutable plan for two launches. Separate plans got the launch count back to 1. Canceling the extra launch still emitted a termination request with an empty instance ID. The proposed patch cancels pending launches locally. github.com/ray-project/ray/p…
3
28
Hi 👋 We prove AI-written code works, so you can ship it without reading every line. Starting today: one real bug a day that we found, fixed and proved.
1
8
80