JackTechie

Hacking M

[JackTechie @jacktechnie]

@dotpem @0xmaz_ @AnthropicAI claude opus 5.5 these days extremely slow. Not sure whether they are planning to introduce UltraFast like @OpenAI , making users feel pains first

[Cyber (In)Security @cybersec]

I've decided to finally release my vulnerability hunting methodology that I've been using for several months now, both in testing as well as live engagements with great success.

I was inspired by (and huge congrats to) the @Blackfrost_AI team open-sourcing Cyber-Frost Harness, their reproducible security-agent runtime with procedural skills, an evidence ledger, and isolated Docker targets for red/blue/purple work. 🎉

If you like the Cyber Frost Harness, and want some out of the box vulnerabilty hunting and POC development kit to go along with it - check out my VulnHunter.

It's already loadable: their harness reads standard SKILL.md skills. Point skill_dir at VulnHunter's (or run its installer), and the hunting, falsification, and PoC disciplines load immediately.

Repo: https://t.co/tK2fhcxwrI

CREDITS: This is fork of @CapitalOne original repo. I simply took it a step further on POC development and model agnostic. I'm also actively developing in my forked repo as I make more changes to it and welcome the contributions from the community as well.

I think I'm doing the whole "respect who you give credit to" drama, and I asked my model to double and triple check it. So i can blame the model if its wrong. Otherwise, dont put me on blast on X if i suck at credits. /s

Looking forward to developing on this further with the community.

[JackTechie @jacktechnie]

@LaylaEleira I tempted to upgrade to Pro 500. Thanks for sharing.

[JackTechie @jacktechnie]

@lucastohdev Hope @AnthropicAI does not follow this rip-off route from openAI

[JackTechie @jacktechnie]

@jturntdev I tempted to upgrade to Pro 500. Thanks for sharing.

[JackTechie @jacktechnie]

@tdinh_me Guess two claude MAX can ship more features

[JackTechie @jacktechnie]

@jordanazzow fucking slow. i believe @openai is selling Pro500 by force to attract its UltraFast feature.

[JackTechie @jacktechnie]

@TE701 @sama fucking slow. i believe @openai is selling Pro500 by force to attract its UltraFast feature.

[JackTechie @jacktechnie]

@beichuan96 fucking slow. i believe @openai is selling Pro500 by force to attract its UltraFast feature.

[JackTechie @jacktechnie]

@AldricEverhart @thsottiaux fucking slow. i believe @openai is selling Pro500 by force to attract its UltraFast feature.

[JackTechie @jacktechnie]

@ericvtheg fucking slow. i believe @openai is selling Pro500 by force to attract its UltraFast feature.

[JackTechie @jacktechnie]

@OpenAI • Pro 200 ($200) usage is being cut in half (20× → 10× Plus)
• The old high-end experience now requires the new Pro 500 at $500/month

[JackTechie @jacktechnie]

@arena @AnthropicAI @OpenAI where are you here

[JackTechie @jacktechnie]

@arena Arena UI (Max) has officially reshaped the Pareto frontier 📈✨

Performance Metrics:
• Visual Clarity: Ranked #1 (+126pt gain)
• Information Density: Pareto-optimal
• Legacy Layout: Deprecated

@arena took their classic look and pushed design aesthetics to a brand-new SOTA.

[JackTechie @jacktechnie]

@arena New Benchmark Released: Arena UI v2

System Specs:
- Legacy design deprecated
- Centralized live-signal telemetry
- Optimized for high-density researcher workflows

@arena didn't just update the dashboard, they fine-tuned the entire experience 📈✨

[0xMarioNawfal @RoundtableSpace]

Cloudflare just open sourced a skill that turns your coding agent into a full security auditor, and it picked up 2,428 GitHub stars in a single day.

Repo: https://t.co/7bQxWv63Nu

[JackTechie @jacktechnie]

@spacexai Please create coding plan not tied to Cursor.

[JackTechie @jacktechnie]

@claudeai Congrats! Can I know effort level used in benchmark? Astra should have compute use skill score as it is the one they promoted astra model few weeks ago

[JackTechie @jacktechnie]

@ParanjayMundra @OpenAI has been known models at first few weeks of launch are phenomenal. I still cant believe this is still happening after many models iterations. I even had to check on X whether it is only me or everyone. Thanks so much to @claudeai and it has never upset me.

[JackTechie @jacktechnie]

@aiglesias_ @morganlinton @adenshepard @steipete Thanks for sharing. Thought of trying it eagerly.