LLMs Found to Struggle at Designing Systems That Call Other LLMs
Start here
A Hacker News post argues that large language models are poor at designing software that invokes other LLMs, often building doomed symbolic systems instead of making a simple model call. The author cites a memory-contradiction tool where Claude iterated for weeks on an impossible solver approach, and his own Autodeck agents reaching for regex over LLM calls. He attributes the pattern to pre-LLM training code, RLVR environments lacking API access, and weak software design. These are the author's claims, not independently verified results.
Generated from reports · updated 18 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AILLMs Are Terrible at Designing AI Systems
LLMs struggle to design software that calls other LLMs, often building doomed symbolic systems instead of making a simple model call. The author cites a memory-contradiction tool where Claude iterated for weeks on an impossible solver approach, and his own Autodeck agents reaching for regex over LLM calls. He attributes this to pre-LLM training code, RLVR environments lacking API access, and weak software design.
Heat for this event
- Current, comparable range
- 6
- Peak, comparable range
- 10November 17 15:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.