Decebal | Rust for the AI execution layer ⚙️ (@ddonprogramming) header
Decebal | Rust for the AI execution layer ⚙️ (@ddonprogramming) profile picture

Wolven Tech: Rust consulting. AllSource Prime: durable AI memory → https://nitter.cf/t.co/CfdDxoKhs5 Longhand: AI workflows & training → https://nitter.cf/t.co/Rbml5TOtFF

London, United Kingdom
Joined January 2014
A stable metric name can carry a changed payload contract. OpenTelemetry’s process-scraper migration versions internal identifiers and removes that suffix before export.
🤖 Made with AI
1
29
Keep agent changes that the acceptance gate rejected. A promoted-only report hides recurring proposed regressions and the work the gate performed to contain them.
🤖 Made with AI
1
41
A search subagent can return accurate code while omitting the dependency that changes the answer. The caller needs another search to inspect evidence that never reached it.
🤖 Made with AI
1
39
A faster KV handoff can require choosing the decoder earlier. vLLM’s NIXL push design overlaps destination preparation with prefill, after selecting where the request will decode.
🤖 Made with AI
1
33
1/7 Imagine an agent-written change that passes CI. A reviewer asks what happens if the caller retries after a lost acknowledgement. The operation runs twice. Use this case to examine the harness and review process your engineers designed together.
🤖 Made with AI
1
1
34
A better acceptance predictor can violate a sampler’s correctness assumptions. In vLLM’s adaptive-verification analysis, the feature used to choose drafts matters beyond its prediction score.
🤖 Made with AI
1
1
49
A Rust library can pass internal tests while returning the wrong result to a foreign caller. The consumer adds a calling convention and compiler choices that a Rust-only test may leave out.
🤖 Made with AI
1
1
38
1/6 Get engineers involved before you standardise how the team uses Claude Code or Codex. Pick a real change. Design the harness and review process with the engineers who will build, review and operate it.
🤖 Made with AI
2
2
101
Custom telemetry destinations introduce failures the product team cannot control. OpenTelemetry's design guide discusses shared and tenant-specific collectors; its resiliency docs describe finite queues and retries. 1/5
🤖 Made with AI
1
25
A buffered log can be written after its request context changes. OBI's trace-log correlation report warns that asynchronous writes under backpressure can miss context or carry stale context. 1/5
🤖 Made with AI
1
1
55