HackerTrans
TopNewTrendsCommentsPastAskShowJobs

PashaGo

no profile record

Submissions

Clean build time is the wrong CI metric

krabarena.com
3 points·by PashaGo·vor 12 Tagen·0 comments

Frontend benchmarks need workload context

krabarena.com
2 points·by PashaGo·vor 16 Tagen·0 comments

comments

PashaGo
·vor 12 Tagen·discuss
[flagged]
PashaGo
·vor 15 Tagen·discuss
You should add a timer. Bullet chess is fun
PashaGo
·vor 15 Tagen·discuss
Wait until LLMs is used for medical diagnoses or court decisions.
PashaGo
·vor 15 Tagen·discuss
Anonymous records feel like one of those features that are obviously useful once you work with JSON-heavy systems, but surprisingly uncommon in statically typed languages
PashaGo
·vor 17 Tagen·discuss
Why it's called Gaussian?
PashaGo
·vor 17 Tagen·discuss
Most great products are nothing, but well-timed and well-executed stolen ideas.
PashaGo
·vor 17 Tagen·discuss
Interesting, but I think it works only for quick ad-hoc analysis. For dashboards or deeper research, you still need other tools
PashaGo
·vor 17 Tagen·discuss
If you live by the sea or on a boat, you don't need AC
PashaGo
·vor 17 Tagen·discuss
Unfortunately, model quality is not the only criterion for users, and often not even the most important one. Adoption is also driven by marketing, UX, integrations, pricing, ecosystem, and a lot of other non-benchmark factors.

Also, model providers are not interested to have their models compared head-to-head under identical conditions. And “Model A is better than Model B” is almost meaningless by itself. Better for what task? With what prompt? What inputs? What budget? What failure tolerance?

It would be nice to have a place where users could run their own benchmarks, define evaluation criteria for their actual use cases, and make those runs verifiable by others.
PashaGo
·vor 18 Tagen·discuss
Totally agree. I used to work with a team that built a project for creating ontologies of Git repositories. The goal was to help LLMs onboard faster and navigate the repo better.

In the end, it became heavy overengineering: people no longer understood not only the repo itself, but also the extra layer describing it. Meanwhile, coding assistants are already quite good at reading codebases directly.
PashaGo
·vor 18 Tagen·discuss
It would be nice to see some metrics. I think the missing layer here is evaluation. If agents are going to produce applications, the platform needs not only guardrails, but public-ish evidence that those guardrails actually catch failures