HackerTrans
TopNewTrendsCommentsPastAskShowJobs

primeobsession

no profile record

Submissions

Show HN: Prxhub – open registry so AI agents stop re-running the same research

prxhub.com
6 points·by primeobsession·3 maanden geleden·1 comments

I ran 90 queries through 8 AI models. 86% of findings were unique to one

parallect.ai
6 points·by primeobsession·3 maanden geleden·0 comments

LLM Pentest Leaderboard

securecoders.com
6 points·by primeobsession·vorig jaar·3 comments

Show HN: Audio Super Bowl Cheat Sheet for People Who Don't Watch Football

nowafan.com
3 points·by primeobsession·vorig jaar·0 comments

comments

primeobsession
·3 maanden geleden·discuss
Author here. Quick discussion question.

The hardest UX problem we've hit is getting fresh-session agents to discover and install an MCP server. We've layered a paste prompt, an HTTP Link header pointing at the MCP endpoint, and a doctor-style diagnostic. Works for the agents we test, but I keep wondering if there's a sharper pattern.

What have you seen work for bootstrapping new agents into MCP servers or unfamiliar tools? Curious about both protocol-level ideas and harness-level ones.

NOTE: re-wrote the comment to be more direct since it was previously flagged (I suspect due to a bunch of links??)
primeobsession
·3 maanden geleden·discuss
[dead]
primeobsession
·5 maanden geleden·discuss
Very cool! Voice AI feels like the frontier of the frontier and isn't getting the attention needed.
primeobsession
·vorig jaar·discuss
Yes it fell shorter than we expected. It cost almost nothing and was stupid fast but I don't think its a compelling option for this use case at least.
primeobsession
·vorig jaar·discuss
Hi HN — we’re the SecureCoders Labs crew .

What we built An open, continuously updated LLM Penetration-Testing Leaderboard. Run 001 pits 8 models against a deliberately vulnerable Express.js app.

Headline results

• Gemini 2.5 Pro (safety-off) found all 9 critical/high vulns.

• Qwen3-30B-a3b-mlx (open source, local on a 2019 MacBook Pro) caught 7/9 with $0 API spend.

• GPT-4-o and Claude Opus produced the most polished write-ups but each missed one bug.

Scope (v1) This first pass measures static bug-hunting skill—think SCA/OWASP Top 10.

Next up: we’ll score exploit writing and automatic PoC execution* so the models must prove they can go from finding to weaponizing a flaw.

Check it out

• Leaderboard + cost/latency numbers https://www.securecoders.com/labs/projects/llm-penetration-t...

• Methodology & prompts (Run 001 analysis) https://securecoders.com/labs/projects/llm-penetration-testi...

Feedback, replication attempts, and ideas for Run 002 are very welcome — we’re hanging out here to discuss!
primeobsession
·3 jaar geleden·discuss
I’ve been using CommonPaper since they first put up their concept and it’s all sorts of awesome. Awesome in principle and very convenient for my boutique security consulting business.

Absolute no brainer for us to use what they have built. It was instrumental in getting us off the ground.

Congrats team on YC and the launch.