Romee Panchal (@romitheguru) header
Romee Panchal (@romitheguru) profile picture

AI Architect | Writer, thinker, and lifelong learner. Subscribe to my newsletter: https://nitter.cf/t.co/1uuir2x6fZ

Bengaluru, India
Joined September 2018
Coding agents are very good at building what you ask for. The gap between what you specify and what you expect is where the agent starts making assumptions. More assumptions → more rework → more iterations → more tokens. The clearer the specification, the closer the output.
🤖 Made with AI
1
165
Master the following 6 patterns to build reliable AI systems
3
238
AI systems are increasingly becoming distributed systems with probabilistic components. The hard part is no longer the model. It’s: - orchestration - reliability - memory/state - evaluation - observability - human oversight LLM calls are easy. Production systems are not.
🤖 Made with AI
1
97
Your AI demo works. Your AI system won't. The gap isn't the model. It's everything around it. Evaluation. Retrieval. Drift. Observability. Structured outputs. The model is the easiest part to replace. The system is not. Read the full article here 👇
2
1
148
LLMs from the ground up
1
11
374
The dumbness of @Swiggy agent is frustrating.
1
150
Paper Summary: 1. LLM hallucinations stem from the fact that even with perfect (error-free) training data, the cross-entropy objective forces the model to guess plausible outputs — binary classification errors are inevitable under epistemic uncertainty. 2. In post-training, models are incentivised to “guess” rather than abstain (e.g. say “I don’t know”) because benchmarks use hard accuracy (0-1) scoring, rewarding confident but possibly wrong answers. 3. The fix: change evaluation design — explicitly reward uncertainty or abstention (via confidence thresholds) instead of punishing it, so models are not forced into hallucinating to win.
3
3
1
26
1,304
Re-reading the article "How to build effective agents". anthropic.com/engineering/bu…
5
394
Cost-effective AI models for agent development: How reliable though?
8
494
Three Main Orchestration Patterns Sequential: Agent A → Agent B → Agent C. Like an assembly line. Parallel: Agents A, B, C work simultaneously. Fast, but coordination is complex. Hierarchical: Manager agents oversee worker agents. Scales well, adds layers.
10
422