Georg Heiler
@geoheil.com
260 followers
1K following
130 posts
building socio-technical complex systems with data | geoheil.com
Posts
Media
Videos
Starter Packs
Georg Heiler
@geoheil.com
· 4d
feat: build SLURM integration for dagster by HPicatto · Pull Request #19 · ascii-supply-networks/dagster-slurm
Type of Change feat: New feature fix: Bug fix docs: Documentation style: Code style refactor: Code refactor perf: Performance improvement test: Tests chore: Maintenance Description adds ...
github.com
Georg Heiler
@geoheil.com
· 4d
Georg Heiler
@geoheil.com
· 4d
Georg Heiler
@geoheil.com
· 17d
Introducing SedonaDB: A single-node analytical database engine with geospatial as a first-class citizen - Apache Sedona
Apache Sedona is a cluster computing system for processing large-scale spatial data. Sedona extends existing cluster computing systems, such as Apache Spark, Apache Flink, and Snowflake, with a set of...
sedona.apache.org
Reposted by Georg Heiler
Georg Heiler
@geoheil.com
· Aug 20
Georg Heiler
@geoheil.com
· Jul 24
Georg Heiler
@geoheil.com
· Jul 20
Reposted by Georg Heiler
Georg Heiler
@geoheil.com
· Jun 24
Reposted by Georg Heiler
![Principle 3 is that Agent actions and planning must be observable. I love this principle—emphasis mine:
We cannot ensure an agent is acting faithfully or diagnose problems if its operations are entirely opaque. Therefore, agent actions, and where feasible, their planning processes, must be observable and auditable. [...]
Effective observability also means that the properties of the actions an agent can take—such as whether an action is read-only versus state-changing, or if it handles sensitive data—must be clearly characterized. This metadata is crucial for automated security mechanisms and human reviewers. Finally, user interfaces should be designed to promote transparency, providing users with insights into the agent’s “thought process,” the data sources it consulted, or the actions it intends to take, especially for complex or high-risk operations.
Yes. Yes. Yes. LLM systems that hide what they are doing from me are inherently frustrating—they make it much harder for me to evaluate if they are doing a good job and spot when they make mistakes. This paper has convinced me that there’s a very strong security argument to be made too: the more opaque the system, the less chance I have to identify when it’s going rogue and being subverted by prompt injection attacks.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:kft6lu4trxowqmter2b6vg6z/bafkreigcurppvz57l3mkonmdvcvos4czcyxm7xokhkh6th6dojtbkp3byu@jpeg)