Dvir Sasson
111 posts


@colinarms @colinarms Went crazy with Codex and took it way too far. Check out the opened PR, I think we have a contender for OpenAI's Symphony
English

I ran Codex, Claude, and Gemini on the same PR review.
They disagreed on 4 out of 7 issues.
That’s when I realized the best workflow isn’t choosing one model - it’s making them compare notes.
So I built Council: an open source CLI that runs all three in parallel, surfaces disagreements, and gives you one synthesized recommendation.
npx @armstrng/council review this PR
English

Hey @grok in 24 hours pick 2 random people from my comments to win $8000 each
Both winners must be following
Thanks you.

English

Just shipped adversarial-spec, a Claude Code plugin for writing better product specs.
The problem: You write a PRD or tech spec, maybe have Claude review it, and ship it. But one model reviewing a doc will miss things. It'll gloss over gaps, accept vague requirements, and let edge cases slide.
The fix: Make multiple LLMs argue about it.
adversarial-spec sends your document to GPT, Gemini, Grok, or any combination of models you want. They critique it in parallel. Then Claude synthesizes the feedback, adds its own critique, and revises. This loops until every model agrees the spec is solid.
What actually happens in practice: requirements that seemed clear get challenged. Missing error handling gets flagged. Security gaps surface. Scope creep gets caught. One model says "what about X?" and another says "the API contract is incomplete" and Claude adds "you haven't defined what happens when Y fails."
By the time all models agree, your spec has survived adversarial review from multiple perspectives.
Features:
- Interview mode: optional deep-dive Q&A before drafting to capture requirements upfront
- Early agreement checks: if a model agrees too fast, it gets pressed to prove it actually read the doc
- User review period: after consensus, you can request changes or run another cycle
- PRD to tech spec flow: finish a PRD, then continue straight into a technical spec based on it
- Telegram integration: get notified on your phone, inject feedback from anywhere
Works with OpenAI, Google, xAI, Mistral, Groq, Deepseek. Leveraging more models results in stricter convergence.
If you're building something and writing specs anyway, this makes them better.
Check it out and let me know what you think!
github.com/zscole/adversa…
English

Ok @DefconParrot breakfast is over. Come find @bitstr3m at the embedded systems village and tell him what he had for breakfast. Grab a coin.
English

#defcon33 #badgelife blackhole badges by #kaizenlabs is ready to go for pickup on preorders starting tomorrow 🔥



Paradise, NV 🇺🇸 English

@ANDnXOR Checkout is currently unavailable due to technical problems. Please try again in a few minutes.
Close
English

What city should we pull up to first?
the travel guru🦋@ExquisiteYardie
nothing, just here wishing i could see @inglewoodSiR in concert again
English

@Krenner @_FreeWili_ @ICS_Village Yessss!!!! You sold it to me and you threw an ICS shirt as well XD
English

Did you buy a @_FreeWili_ and/or an @ICS_Village #WhaleTale badge?
If so, reply or tag me in posts of you using/learning/enjoying it!!
I (or my husband) probably sold it to you. I want to be in on the fun.
🐳
#BadgeLife

English













