Nicheloom visits: 60,536 all-time · 7,913 in the last 7 days

The opportunity tracker for new startups.

Today: 895 launches · Niche of the day: browser-based video games · See what launched today →

Benchmark: AI doesn't find bugs unless you tell it what's wrong

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

New benchmark from researchers at Meta, Stanford, Harvard, UW, including the researchers who've worked on SWE-bench, ProgramBench etc.Most benchmarks just test if AI can fix a problem you've already pointed out.But obviously it would be much better to fix problems before you or any user runs into it. Like, isn't it crazy that we still have to wait for people to open tickets before a lot of obvious bugs get found?We wanted to test that capability at scale. Turns out that models still are terrible at it (best setup we tested still fixed < 5% of bugs)We have 100 repos of 22 languages and 4k bugs between. All the bugs are real-world bugs from github. We do a lot of filtering to ensure everything can be solved in this setting.===========================================Sol 5.6 (xhigh) 4.7% $7,230Luna 5.6 (xhigh) 2.5% $224Terra 5.6 (xhigh) 1.5% $357Luna 5.6 (high) 1.4% $28Opus 5 (xhigh) 1.3% $5,363Kimi K3 0.6% $2,451Luna 5.6 0.5% $4GPT-5.4 Mini (high) 0.5% $122GPT-5.4 Mini 0.2% $5Gemini 3.5 Flash Lite 0.1% $6===========================================Also the best model is very expensive.We have a lot more FAQ on the website https://swesweep.com/ Oh and we're all open-source (MIT license) at https://github.com/facebookresearch/swe-sweepCurious what you all think!

HN · launched Oct 1, 2026 · 5 upvotes (top 90%) · 0 views

Niche: ai benchmarking platforms · 146 launches, 4 in the last 7 days ▼ -56% · Explore this niche →

Category and tags

  • Horizontal
  • Observability & eval
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

Could you build this?

No SWE-sweep is a massive research benchmark spanning 100 repositories and over 4,000 verified bugs, requiring deep program analysis, harness execution sandboxes, and academic rigour.

What it would actually take: Constructing this benchmark requires automated repository mining, regression test generation, and complex isolated Dockerized execution environments to reliably verify multi-bug codebases. It demands significant systems and software engineering expertise, alongside thousands of dollars in cloud/LLM evaluation compute to benchmark models.

Discussion

2 comments analyzed.

Concerns raised: Models hallucinating fixes on unbroken code

Feature requests: Show precision alongside recall on the leaderboard

Competitors

Other products that read as similar to this one : 304 launches clear the similarity bar, closest 8 shown.

Attention rank: #292 of 305 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 336 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.