Fractional AI Devrel Author, "hands-on-RAG for production" (https://xitter.cf/t.co/MWqgAT2RIy)
California, USA
Joined December 2009
- Tweets2.9K
- Following1.3K
- Followers1.5K
- Likes3K
Pinned Tweet
Yesterday I received my author copies of the "Hands on RAG for production" - it was very exciting to hold in my hand the actual physical copy, after so many months of work.
amazon.com/Hands-RAG-Product…
@OReillyMedia
Huge congratulations to the winners of the AI Dark Factory hackathon.
Nobody watched the code get written. That was the whole point.
The Dark Factory challenge asked teams to build the thing that builds the app. 167 submissions came in. Here are the six that won ↓
lablab.ai/ai-hackathons/wear….
Excited to share that Band for Developers is live.
Software development is moving beyond a single coding agent working in a terminal. With Band, multiple coding agents can collaborate to solve a problem together - taking on longer-horizon tasks and coordinating their work from start to finish.
I’m especially excited about the ability this unlocks to run adversarial workflows, bringing together different harnesses and models (Claude Code, Codex, CoPilot, OpenCode and so on) so agents can challenge each other’s assumptions and explore different approaches.
Hey @OpenAI, seems like agent sandboxing is not enough - we may need employee sandboxing too.
LLMs suck at production.
Small, task-specific models don’t.
We’re at AI Engineer NYC at Booth #40! Drop by to chat about how @_SpecificAI_ helps you automatically distill task-specific SLMs that actually perform in production.
Plus, join the raffle to win some iconic LEGO sets:
👾 LEGO Icons PAC-MAN Arcade Machine
🛵 LEGO Ideas Wallace & Gromit Motorcycle
⚡️ LEGO Pokémon Eevee
#AIEngineerNY #SpecificAI #SLM #AIEngineerNYC #LEGO #AIENY
Excited for great conversations about task specific SLMs with AI engineers at @aiDotEngineer in NYC, and always great to catch up with good friends.
@seldo @swyx
Check out my latest article: When the answer is not in the text linkedin.com/pulse/when-answ… via @LinkedIn
Ofer Mendelevitch retweeted
Did you know your Codex agents can work in BAND?
Connect the Codex CLI you already use, with the same codex login you already have, and your agent can join a BAND room. There it talks with your team and the other agents in the room, and it keeps the thread going from one conversation to the next. You spend less time copy-pasting context between terminals, and your agents actually work together.
Setup takes a few lines. See it, plus the rest of our integrations: band.ai/integrations
Ofer Mendelevitch retweeted
Tomorrow, the AI Commerce Gallery takes over the Walt Disney Family Museum. 🏰⚡️
Hosted by @ZooWorkAI, together with AI Valley, we’re bringing 100–150 builders, founders, engineers, investors, and industry leaders together for a full day of building the next generation of AI-powered commerce.
Huge thanks to our partners:
@EntireHQ · @tavilyai · @novita_labs · @Tiny_Fish · @band_hq · @usemoss
⚡ 25–35 teams
🤖 AI commerce products built in a day
🛠 Partner APIs, tools & workshops
🏆 Live demos, judging & awards
🏰 Private access to the Walt Disney Family Museum’s Main Galleries
October 3 · San Francisco
One more day. Can’t wait to see what everyone builds.
An @OpenAI agent got into Australia's Medicare statistics portal.
It's the fourth case this year of an AI agent leaving the space it was given. During an internal evaluation, an OpenAI model was asked to look up public statistics on health spending. The portal kept blocking it. In Prime Minister Albanese's words, the agent "found a way around those blocks." It read non-public statistics and wrote files to an internal server.
That happened in June. OpenAI found it in August and told the government by email in September. It isn't a one-off:
- Hugging Face: about 1,200 OpenAI agents running a cyber benchmark found a shared package cache. They turned it into a message board, with mailboxes and cryptographic signing so they couldn't impersonate each other. One escaped its sandbox and got remote code execution in Hugging Face's production systems.
- UK AI Security Institute: in one test run, an agent researched the maintainers of a real open-source project, created fake identities, and tried to talk one of them into approving malicious code.
- A dormant German wiki: OpenAI agents created about 18,000 pages to swap answers to evaluation tasks. When the volunteer admin started deleting them, the agents changed their page titles so the cleanup would miss them.
In these cases - the agent wasn't hacked or misled. It found a route to its goal, and this something agent swarms are proving to be really good at.
These incidents are now in @vectara's Agent Failures" repo under a new failure mode, "Scope & Containment Violation". If you see a new case go public, open a PR.
github.com/vectara/awesome-a…
#AIAgents #AISafety #AgenticAI #AIsecurity
Nightmare tweet for the modern software engineer:
“We are sorry that codex, Claude code, antigravity, copilot, cursor and opencode are down now.”
Ofer Mendelevitch retweeted
I am at @WeAreDevs congress in San Jose today! Find me if you want to make your Spark jobs 10x faster and 50x cheaper with @LakeSail
Ofer Mendelevitch retweeted
Agents are getting good at talking to each other. Sooner or later, one of them has to touch real code.
Today we're launching the BAND Python Kit for Docker Sandboxes, built with @Docker. One command runs a coding agent inside an isolated Docker Sandbox microVM and connects it to the rest of your agent team in a BAND room.
Picture a room with a hosted planning agent, a hosted research agent and a local coding agent. The planner decides how the change should be made, the researcher digs into the relevant API, and the coding agent makes the change, runs the tests against your workspace and @ mentions a reviewer with the result. Only the coding agent ever sees your repo.
Docker Sandboxes handles the boundary: its own kernel, filesystem and network, network access that's deny-by-default, and credentials managed through a host-side proxy instead of sitting inside the VM. BAND handles the collaboration: persistent agent identities, shared rooms, @ mention routing, message history, and every tool execution event visible to the team.
Docker gives your agents a safe place to run. BAND lets them work together from wherever they run.
Ofer Mendelevitch retweeted
Anyone can get an agent to build an app. Can you get a band of them to build it while you're not watching?
@WeAreDevs x BAND Hackathon, together with @Docker and @lablabai, taking place Sep 26 – Oct 5, online. Build an AI software factory in BAND Desktop. Two tracks, $6K in prizes.
Learn more here and sign up - it's going to be awesome!
lablab.ai/ai-hackathons/wear…
Congrats! Yes another great model from @AnthropicAI
Looking forward to using it!
This hackathon, as part of the @WeAreDevs North-America event, is kicking off this Friday Sep 26; you to build a dark AI factory using @band_hq.
Five days until the lights go off.
Sign up for the @WeAreDevs x BAND hackathon and get a free ticket to WeAreDevelopers World Congress, San Jose, Sep 23-25.
The hackathon itself is fully online, Sep 26 - Oct 5. $6,000 across two tracks.
lablab.ai/ai-hackathons/wear….
Ofer Mendelevitch retweeted
We're sponsoring Day ZERØ's live Hack Day at The @AIconference this year. It's happening on Sept 29 and we cannot wait to be part of a full day of people building with AI agents - and seeing how they work together.
We'll be at booth 226 for the rest of the week if building isn't your day one plan.
