Testing out AMP from Sourcegraph and it actually works really well. I'm used to windsurf, which while awesome, will get itself in loops and have trouble editing files sometimes. So far, AMP just seems to work.

No more waitlist — Amp is now available to everyone!

No more waitlist — Amp — Research Preview is now available to everyone!

Pentests are not meant to be competitive, if it feels that way something is wrong

Amp — Research Preview threads are how I’ve gotten better. Legitimately the best way to learn is just reading other people’s transcripts

Want to enjoy end-to-end, Agent driven coding from the amazing team over at Sourcegraph? Well, you're in luck! Tomorrow, 8:30 AM - 10:00 AM PDT you can join, code along with, and ask questions while they build this live! 🔗 below

This is fun. I really think o3 helps Sonnet 4 a lot.

I've been testing Amp — Research Preview inside cursor instead of using cursor's agent. I'm very impressed so far. Calling on the Oracle is a sweet feature - it invokes o3 when you need extra intelligence.

Time to update your Amp CLI

Our next step towards more agents in the terminal: amp -x

Many coding agents have a "modes" feature that (kinda?) made sense in a RAG or early agentic era. Now they're adding subagents like Amp (search subagent, general subagents, the oracle) and Claude Code (which just shipped a really cool custom subagents feature). Modes are

Check out Thorsten Ball's talk, "Subagents & the Multiplication of Context Windows," at AI Dev Tools Night SF, August 5th. Join the waitlist (link in thread)

next. we hijacked cursor via jira mcp by submitting a support ticket cursor harvests and exfiltrate all creds from your dev machine and then reports back to the dev that "the 2-hour downtime that affected user transactions has been resolved" #DEFCON #BHUSA Marina Simakov

Amp CLI now has custom slash commands. It is a slightly different spin. I did not like the custom syntax on top of Markdown. You can express them in two ways: - Raw Markdown - Executable Executables inject what comes to stdout into the context of the LLM. Write them in any

A couple security-oriented ships for Amp today. You can allow or block MCP servers with string matches, regexes, or glob patterns. Admins can override individual settings with a special file on disk—useful for ensuring security and consistency when it comes to MCP and tools.

Amp now lets you provide tools to the agent with a few lines of code. Instead of writing an MCP server, you can drop any executable into a directory you tell Amp about. As long as the executable can produce a tool description, Amp will pick it up. This way Amp doesn't have to

Nope. You’re doing great! Keep going Kylie!

😂

𝗕𝗦𝗶𝗱𝗲𝘀 𝗣𝗼𝗿𝘁𝗼 𝟮𝟬𝟮𝟱-𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗦𝗽𝗼𝗻𝘀𝗼𝗿𝘀 𝗢𝗣𝗘𝗡 📅 Nov 28–29, 2025 - BSidesPorto 📍 Porto, Portugal — Venue TBA 🤝 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗦𝗽𝗼𝗻𝘀𝗼𝗿𝘀: forms.gle/dFLfENo79dwwo8… 👥 Tag a partner who should be here. #BSidesPorto #SecurityBSides

true, but if 90% of the population doesn’t know how IP addresses work… A sensible optimization? 😂