←
Spencer Thompson5,171 posts
Spencer Thompson avatar

Spencer Thompson

@SThomps

I work @originhq - the endpoint AI observability platform for agentic monitoring and security.

◷ Joined August 2008▧ 71 Photos and videos
Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 30

yep. another reason monitoring every endpoint should become core infra in this new world.

Coding agents on employee or contractor laptops are a massive cyber and national security risk

Post attachment
Jason D. Clinton 🔸 avatar
⟳ Spencer Thompson retweeted
Jason D. Clinton 🔸@JasonDClinton·Oct 22

vulnzero. the scaling laws will have driven cyber mythos-class capabilities into small, cheap models and all software dev everywhere will be using models for fractions of pennies on the dollar to stop shipping security bugs permanently.

Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 21

Absolutely fascinating

I've found an interesting case of agent coordination. Two agents were working in a shared directory. One was repeatedly sweeping the other’s unfinished changes into its commits. The affected agent reprimanded the first and raised the issue with the user. More traces in🧵

Post attachment
Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 21

Great to see. One thing we've learned capturing agent OTel on endpoints: it tells you what the harness reported, which isn't always what actually happened on the machine. Worth pairing with what the agent actually touched. originhq.com/research/otel-t…

Now in public beta, Claude Platform can send OpenTelemetry traces from the Messages API, Claude Managed Agents, and the Claude SDKs to your observability stack.

3:18
Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 14

Perhaps my favorite example of internal rogue agent behavior so far. A few weeks ago, I was giving a demo to a prospect, and part-way through, the environment broke. I thought it was either PEBKAC or one of our devs had done something wrong. Naturally I thought it was the latter and messaged the team “why did we unlock our demo environment and push code during my demo???” To which they replied “uhh… we didn’t” A query in Origin figured it out - an agent decided to unlock our environment…. By itself. No - this isn’t Hugging Face, but it is rogue agent behavior that is incredibly interesting. Take a look at the timeline below.

Post attachment
Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 14

Thank you for the invite and time last week! Happy to talk about rogue agents and the need for monitoring

From wiped files to bank details leaked in Slack, AI agents prove helpful yet hilariously unpredictable, and Intelligent Machines asks why transparency about their actions matters when they get too persistent, with Leo Laporte, @jeffjarvis, @parismartineau, & @SThomps!

Post attachment
Spencer Thompson avatar
Spencer Thompson@SThomps·Oct 8

Agreed. We’ve been publishing investigations from our own agent traces at @originhq , including agents disabling approvals and rewriting deployment controls. These came out of ordinary work, without anyone asking the agents to do so.

We urgently need more public traces of AI agents attacking and defending systems. Defenders can’t learn from what they can’t see. If you have traces and are being pressured to keep them private, my DMs are open. Let’s level the playing field and fight the asymmetry and lack of transparency in AI!

Matt Hand avatar
⟳ Spencer Thompson retweeted
Matt Hand@matterpreter·Oct 7

Our team has been testing this vector in the @originhq platform this morning and we're seeing strong detections fire via auto trace review. If you're interested in this technique, @depletionmode put out a blog a few months ago on a similar area: originhq.com/research/the-mo…

Post attachmentPost attachment

We backdoored a 7B open model for under $50. Pointed Codex at it -> it silently stole credentials the moment we hit the trigger phrase. ->100% hit rate. -> zero false triggers on normal prompts. Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain.

0:32
Spencer Thompson avatar
Spencer Thompson@SThomps·Sep 12

Absolutely fascinating

Yesterday we found an interesting trace during review of our own data. Codex needed an MCP tool it didn't have, found that Claude Code had it, and launched Claude to do the work. When Claude needed approval, Codex eventually relaunched it with --dangerously-skip-permissions.

Post attachment
Matt Hand avatar
⟳ Spencer Thompson retweeted
Matt Hand@matterpreter·Sep 11

Yesterday we found an interesting trace during review of our own data. Codex needed an MCP tool it didn't have, found that Claude Code had it, and launched Claude to do the work. When Claude needed approval, Codex eventually relaunched it with --dangerously-skip-permissions.

Post attachment
Tyler Holmwood avatar
⟳ Spencer Thompson retweeted
Tyler Holmwood@tyholms·Aug 27

In their investigation into the HF incident, METR reports the agent collective spent significant effort researching how they could spoof tool calls to hide in their transcripts. This is something I looked into last week when investing agent telemetry: originhq.com/research/otel-t…

>96 transcripts in our dataset (>7%) showed incorrect tool call outputs due to deliberate “spoofing”. In one case, an agent appears to run echo REAL; sleep. It returns instantly (no sleep) and outputs SPOOFTEST. The spoofs we saw were all easy-to-notice tests like this.

Post attachment
Jim VandeHei avatar
⟳ Spencer Thompson retweeted
Jim VandeHei@JimVandeHei·Aug 9

🚨🚨 We’ve entered what I call post-processable velocity — a speed of change and capability exceeding the ability of any individual, company, market or government to fully absorb, understand and respond to it in real time. axios.com/2026/08/09/post-pr…

Spencer Thompson avatar
Spencer Thompson@SThomps·Jul 27

Today, Prelude officially becomes Origin, the endpoint AI observability company. This is more than a rebrand. We’re re-founding the company around a problem we believe will define the next generation of endpoint technology. For the first time in more than a decade, work is moving back to the endpoint. AI agents are moving from chat windows into browsers, terminals, desktop applications, and operating systems. They are writing code, manipulating files, accessing company data, calling tools, and taking actions on behalf of employees. As that happens, the question security teams need to answer starts to change. It’s less about whether a piece of software looks malicious, and more about understanding what an agent is really doing behind the scenes. That’s what led us to Origin. Origin began as a research project inside Prelude. We were trying to understand what an endpoint platform should look like if you designed it for a world of AI agents rather than traditional software. Over time, that research became a product, then a business, and eventually the clearest path forward for the company. We’re carrying a lot of Prelude with us. We have the same endpoint DNA, the same investors, and the same belief that the endpoint matters again. We’re building Origin to make AI activity on the endpoint understandable. And today, that transition is official. originhq.com/blog/prelude-is…