Viewing profile — thomaslwang
thomaslwang
HN member- Joined
- Mon, Jul 07, 2025, 8:34 AM UTC
- HN karma
- 3
- Public activity
- 20 items
- HN profile
- View on Hacker News ↗
About thomaslwang
No profile information was provided.
Recent public activity
-
story
Show HN: OpenThomas – weather trader agent for prediction markets
An open-source agent that forecasts station temperatures and trades them. Build in public & trade in public. Site: https://openthomas.com Repo: https://github.com/PredictionMarketT…
-
comment
Comment #48832263
This reminds me of the old "code on a shirt" tradition - MIT used to sell shirts with Lisp one-liners. What I find interesting is that the script actually runs. Most of these novel…
-
comment
Comment #48832138
[dead]
-
comment
Comment #48728322
[dead]
-
comment
Comment #48305900
[dead]
-
comment
Comment #48305898
[dead]
-
comment
Comment #47573380
[dead]
-
comment
Comment #47573373
[dead]
-
comment
Comment #47570729
[dead]
-
comment
Comment #47570714
[dead]
-
comment
Comment #47569177
[dead]
-
comment
Comment #47513947
[dead]
- story
-
comment
Comment #47436425
HiddenLayer 2026 AI Threat Landscape Report: Autonomous agents now account for more than 1 in 8 reported AI breaches as enterprises move from experimentation to production. 88% of …
- story
-
comment
Comment #47435101
AI agents are leaking credentials and API keys at unprecedented scale - 2865 million secrets exposed to public GitHub in 2025, AI service leaks up 81%. Traditional security framewo…
- story
-
comment
Comment #47427049
Exactly! The challenge is that agents optimize for goals in unexpected ways. MoltGuard adds runtime guardrails to block the unexpected tool calls before they execute. Thanks for th…
-
story
I built a runtime guardrail that stops AI agents from doing dumb things
Most AI security tools detect problems AFTER they happen. I built MoltGuard - runtime guardrails that block dangerous tool calls BEFORE execution. Install: curl -s https://wry-mana…
- story