News for hackers. Stuff that matters.
Re:The agent harness belongs outside the sandbox by tantalor on Sunday May 03, 2026 @12:23AM (#47993318)
> if your harness has an ability to do something the LLM can't

What does this even mean. The only capability of an LLM is generate text.

Re:The agent harness belongs outside the sandbox by jbstack on Sunday May 03, 2026 @04:02AM (#47994584)
The LLM can only generate text. The harness can do more than just generate text. By joining the two you're allowing the LLM (through text) to carry out whatever actions the harness can take.

My brain can only generate electrical signals. My hand responds to electrical signals and can interact with the real world. The two together can do more than just what my brain alone can do.

If you don't trust a particular brain, don't put a gun in the hand which is connected to it. If you don't trust a LLM, don't connect it to a harness which has access to your production database and only recent backups (https://www.theregister.com/2026/04/27/cursoropus_agent_snuf...).

Re:The agent harness belongs outside the sandbox by girvo on Sunday May 03, 2026 @04:52AM (#47994911)
We’ve trained models on JSON schemas for “tool calls”, and then built software to interpret and run those calls for the LLMs
Re:The agent harness belongs outside the sandbox by tantalor on Sunday May 03, 2026 @11:47AM (#47998132)
> software to interpret and run those calls

Yes... That's the harness!