Viewing profile — dial481

dial481

HN member

No profile information was provided.

story
Comment #48745244
Wed, Jul 01, 2026, 11:51 AM UTC
comment
Comment #48567171
This is badly needed. Jira is horrendous. Can your plugin system support custom workflow triggers yet?

Wed, Jun 17, 2026, 7:51 AM UTC
comment
Comment #48559794
[flagged]

Tue, Jun 16, 2026, 6:28 PM UTC
comment
Comment #48554670
[flagged]

Tue, Jun 16, 2026, 1:04 PM UTC
story
Show HN: Allelix – Annotate your DNA against 7 public databases offline
Tue, Jun 16, 2026, 1:03 PM UTC
story
Comment #47936939
Tue, Apr 28, 2026, 4:43 PM UTC
comment
Comment #47716508
MemPalace's benchmark claims have been picked apart and debunked in the project's GitHub issues: github.com/milla-jovovich/mempalace/issues/27 github.com/milla-jovovich/mempalace/i…

Fri, Apr 10, 2026, 11:30 AM UTC
story
Show HN: Proposal for a real long-term AI memory benchmark
Thu, Apr 09, 2026, 4:37 PM UTC
story
Milla Jovovich's MemPalace Claims 100% on LoCoMo. Its Benchmarks.md Disagrees
Tue, Apr 07, 2026, 11:28 AM UTC
comment
Comment #47509119
That's encouraging to hear from someone with IR experience, thanks. Agree completely.

Tue, Mar 24, 2026, 8:54 PM UTC
comment
Comment #47491366
We audited the LoCoMo benchmark (one of the most cited eval for LLM agent memory) and found 99 score-corrupting errors in 1,540 questions (6.4%). Separately, we tested the LLM judg…

Mon, Mar 23, 2026, 4:04 PM UTC
story
LoCoMo AI Benchmark: 6.4% of answer key wrong, judge accepts 63% of fake answers
Mon, Mar 23, 2026, 4:04 PM UTC