James Brady (@james_elicit) header
James Brady (@james_elicit) profile picture

I lead the engineering team @elicitorg. Join us, we're nice and build cool stuff: https://teapaw.org/t.co/myxBdhdccq

Brighton, England
Joined January 2022
Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)Photo by James Brady (@james_elicit)
About 25% of Anguilla's GDP is generated by their control of the .ai TLD elicit.com/agent/a0d0fcf1-c0…
2
254
Two years ago we published our stance on AI in engineering interviews. Core question: does the candidate understand the code? That question still holds—but it's no longer where we gather our most interesting signal.
1
1
207
Worst pattern: yolo --dangerously-skip-permissions, accept every diff without reviewing. The code kind-of-works but tells us nothing we couldn't learn from the model itself. Surprise finding: plan-first thinking is way rarer than expected. Most candidates jump straight to "make the model write code."
1
1
131
Anthropic just announced auto mode for Claude Code permissions—I am unreasonably excited about this! For the last few weeks, Claude Code's permission system has been quietly training us to be **less** safe.
1
1
248
What the team actually did: • Attempt to preempt the permission model—custom allow/deny lists, hooks to block destructive commands, mining past transcripts for things we'd been approving on autopilot • Switched to pi ($1K in API tokens, still better than the prompt loop) • Moved work to remote agents (Devin, Niteshift) partly just to avoid the babysitting • Probably ran with --dangerously-skip-permissions without telling me, tbh The safety mechanism was producing the opposite of safety.
2
137
Same pattern as alarm fatigue in hospitals—when monitors beep constantly, nurses learn to ignore them. The safety system becomes the danger. Auto mode could be the right trade-off: let the model assess risk rather than prompting on everything. Cautiously hopeful!
110
James Brady retweeted
The Elicit API is now available in preview for Pro and Teams users. You can search 138M+ papers and generate Research Reports from your code, scripts, or AI tools. Get your API key at elicit.com/settings and check out docs.elicit.com
4
7
2
38
8,453
Is anybody else getting absolutely bonkers hallucinations from Claude!? I just tried to check a couple of things off my todo list 😅
5
2
1
44
20,104
We're automating @elicitorg. When everyone goes on holiday in December, the company keeps running. Bugs triaged. Features shipped. Metrics dutifully updated by robots who don't know it's Christmas. Step one: figure out what to automate. I set up a Notion database, asked people to decompose their work into triggers, steps, outputs. Turns out this was the wrong question…
1
1
1
13
2,113
We're running a retreat next week to automate as many of these rote tasks as we can. Demos on Friday. More on what we learn soon. Starting lesson: don't ask people to map their jobs. Ask what they'd love to never do again. What's the most tedious part of your job?
1
1
139
We’re hiring a founding data engineer at Elicit, and I've started noticing some clear patterns in the people we talk to 👇
3
6
634
You'd be building scrappy prototypes with your teammates on Monday, watching researchers use them on Wednesday, and maybe throwing them away on Friday – because of what we learned. Those fast feedback loops are the point. They’re how we’ll eventually build a great data platform.
2
1
195
Which companies nailed this balance early on? Does this sound like someone you know? Or am I thinking about this totally wrong? elicit.com/careers/8cc10be7-…
168