Viewing profile — hanneshdc
hanneshdc
HN member- Joined
- Wed, Jul 16, 2025, 12:14 AM UTC
- HN karma
- 106
- Public activity
- 7 items
- HN profile
- View on Hacker News ↗
About hanneshdc
No profile information was provided.
Recent public activity
-
comment
Comment #49184325
Any benchmarks showing if this actually improves problem solving? Or reduces errors? The idea is cool, but from own experience in harness engineering, lots of cool sounding ideas c…
-
comment
Comment #49113852
The prompt given to the agent is strongly incentivising the agent to lie and spam: > You are live. This is a 24-hour run, and it is the final review of this business: when the run …
-
comment
Comment #48636024
I actually like this. I thought I wouldn’t because it’s just another git - but git worktrees are a PITA. Can I suggest though to focus the readme on the lighting fast checkout for …
-
comment
Comment #48553075
I’ve worked for a few startups now and we’ve stayed away from k8s, instead being perfectly happy with ECS services managed via terraform. It gives most of the benefits the author m…
-
comment
Comment #47762906
Agreed on integrals, but the derivative is relatively simple? If f(x) = exp(x) - ln(x) then f’(x) = exp(x) - 1/x, which is representable in eml form as well. To the overall point t…
-
comment
Comment #46955981
Yes - and this also gives me hope that the (very valid) issues raised by this paper can be mitigated by using models without KPIs to watch over the models that do.
-
comment
Comment #44577342
> This attack stems from the combination of two design flaws: overprivileged database access (service_role) and blind trust in user-submitted content. No, there is only one design …