Skip to content

Talk submission: Declan Johnston #32

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
milstan merged 2 commits into from
May 21, 2026
Merged

Talk submission: Declan Johnston #32

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1a7c01c
Add talk: Declan Johnston
declanatinference May 21, 2026
2189510
Merge remote-tracking branch 'origin/main' into talk/31
milstan May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ We invite submissions of **5-minute talks** (including Q&A - nothing fancy - jus
| [**Shashank Agarwal**](https://github.com/imshashank)<br>[noveum.ai](https://noveum.ai) · [𝕏](https://x.com/itsshashank) | AI agents are already silently failing in production — most enterprises just don’t realize it yet. […](https://github.com/milstan/sisw/issues/24) |
| [**Alexandru Turcanu**](https://github.com/pondorasti)<br>[flaco.851.sh](https://flaco.851.sh) · [𝕏](https://x.com/pondorasti) | Making AI multiplayer. Every company wants a self improving AI Agent like [River](https://x.com/tobi/status/2053121182044451016) or [Inspect](https://builders.ramp.com/post/why-we-built-our-background-agent), yet existing harnesses like OpenClaw quickly fall apart the moment you add them in Slack. We’ll explore how we built an agent harness for teams and dive into the details that power it: - thread isolation with sandboxing - shared memory model - capabilities that go beyond MCPs |
| [**Saai Arora**](https://github.com/Saai151)<br>[tryreplicas.com](https://tryreplicas.com) · [𝕏](https://x.com/saaiarora) | We're building replicas which is a cloud coding agent where you bring your own credentials for Claude Code or Codex. Customers like Mintlify and Composio use us to do everything from writing code to E2E testing via automations and integrations with Slack and Linear. Each agent works inside customizable VM environments, so work is parallelized and shareable across the team. Replicas can access sources like databases, Datadog or Notion, and return screenshots and videos as proof of work. |
| [**Declan Johnston**](https://github.com/declanatinference)<br>[inference.net](https://inference.net) · [🔗](https://github.com/context-labs/HALO) | A general-purpose harness like Claude Code is the wrong tool for trace analysis. […](https://github.com/milstan/sisw/issues/31) |
<!-- TALKS:END -->

<!--
Expand Down
23 changes: 23 additions & 0 deletions _data/talks.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,3 +172,26 @@
submitter_github: Saai151
submitted_at: '2026-05-21T18:33:53Z'
issue: 28
- first: Declan
last: Johnston
domain: inference.net
repo: https://github.com/context-labs/HALO
twitter: ''
summary: 'A general-purpose harness like Claude Code is the wrong tool for trace
analysis. This isn’t because the model isn’t smart, but because traces can get
extremely long, and you need a specialized toolkit in order to make observations
about systemic agentic behavior. HALO (Hierarchical Agent Loop Optimization) is
a methodology for building recursively self-improving agent harnesses using RLMs.


The core HALO loop is suprisingly simple:

1. Collect execution traces from your agent harness. HALO uses OpenTelemetry-compatible
tracing.

2. Feed traces into HALO-RLM engine.

3.'
submitter_github: declanatinference
submitted_at: '2026-05-21T20:17:59Z'
issue: 31
Loading