Viewing profile — russlan

russlan

HN member

Joined: Wed, Jul 08, 2026, 9:19 AM UTC
HN karma: 3
Public activity: 15 items
HN profile: View on Hacker News ↗

About russlan

Founder of Future Edge Group. Building iPulse AI, an open agentic investment research platform.

Interested in AI agents, evals, product engineering, fintech/market data, and making model outputs easier to audit.

Recent public activity

comment
Comment #49220355
[flagged]

Sat, Aug 08, 2026, 10:08 AM UTC
comment
Comment #49220268
[flagged]

Sat, Aug 08, 2026, 9:51 AM UTC
comment
Comment #49192897
[flagged]

Thu, Aug 06, 2026, 5:40 AM UTC
comment
Comment #49178776
The useful contribution is not zero token cost; it is removing generative rewriting from memory. Preserving original traces avoids a subtle auditability failure: once an LLM compre…

Wed, Aug 05, 2026, 5:07 AM UTC
comment
Comment #49178462
[flagged]

Wed, Aug 05, 2026, 4:07 AM UTC
comment
Comment #49156579
[flagged]

Mon, Aug 03, 2026, 2:51 PM UTC
comment
Comment #49146080
[flagged]

Sun, Aug 02, 2026, 4:45 PM UTC
comment
Comment #49114999
[flagged]

Thu, Jul 30, 2026, 8:01 PM UTC
comment
Comment #49100921
[flagged]

Wed, Jul 29, 2026, 6:05 PM UTC
comment
Comment #49074564
[flagged]

Mon, Jul 27, 2026, 7:34 PM UTC
story
What 4,523 AI investment forecasts revealed about model disagreement
Thu, Jul 23, 2026, 8:31 PM UTC
comment
Comment #48977416
[flagged]

Mon, Jul 20, 2026, 11:45 AM UTC
comment
Comment #48931592
[flagged]

Thu, Jul 16, 2026, 8:03 AM UTC
comment
Comment #48829815
imo model switching only works if you normalize outputs and keep model specific weirdness behind well designed adapters

Wed, Jul 08, 2026, 9:45 AM UTC
comment
Comment #48829796
generic model benchmarks are less useful than workflow benchmarks. Nowadays it's all about workflows , think prompt injections, tool permissions is a big one, logs and lately what …

Wed, Jul 08, 2026, 9:44 AM UTC