Agentic Trading with Safe Guardrails
jgan0978
47 points
28 comments
May 17, 2026
Related Discussions
Found 5 related stories in 82.4ms across 8,303 title embeddings via pgvector HNSW
- Agent Skills BOOSTERHIDROGEN · 199 pts · May 04, 2026 · 53% similar
- Agentic Engineering fagnerbrack · 22 pts · May 08, 2026 · 53% similar
- Agentic Engineering Patterns r4um · 505 pts · March 04, 2026 · 52% similar
- Agent Skills – Open Security Database 4ppsec · 33 pts · March 16, 2026 · 51% similar
- Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks zambelli · 385 pts · May 19, 2026 · 50% similar
Discussion Highlights (10 comments)
0x5FC3
More ways than one to burn money with agents :)
this_user
Trying to trade with generalist LLMs is just an exercise in futility, because none of these models have ever seen the inside of a real trading firm. None of that knowledge is in their training sets.
mlmonkey
> Plug your agent into the sources where information breaks first. Twitter, Telegram, Discord, on-chain activity. Your agent acts before the market does. In a world where people are fighting with each other to see who can get closer to the trading systems in order to shave off milliseconds, this seems glacial.
victorbjorklund
Using LLM:s to trade makes no sense at all (outside some narrow strategies trying to trade fast on news etc)
la64710
While most folks are quick to write off agentic trading attempts for various reasons, one strength that I see in using LLMs is its capability to bring together disparate information sources and chart a path forward.I do agree it is a very advanced word calculator but that seems to work most of the time unless there is a massive information gap in the original data sources.
torlok
It's there any evidence that trading off of headlines works long-term?
yieldcrv
I agentically track potential catalysts that the market forgets about (judging from implied volatility in the options market) It works AMA
m463
I remember a friend telling me the state highway department used to call them guardrails, but after some lawsuits, they started calling them guide rails. This legal distinction was because they didn't want to imply they could prevent accidents.
jacobr1
Where are the "Safe Guardrails" ?
SpicyLemonZest
I know it's bad manners to point out when "repositories" of "code" are just markdown files, but these are even more pointless markdown than most. They're just telling agents how to use their public, documented API. What is the possible scenario where an agent working with Shuriken would not load "Integrating and building with Shuriken" into context? (Where are the "safe guardrails" in the hallucinated title?)