HackerTrans
TopNewTrendsCommentsPastAskShowJobs

DenisM

12,487 karmajoined 18 tahun yang lalu

Submissions

Kirkland Roundabouts

kirklandroundabouts.com
182 points·by DenisM·27 hari yang lalu·150 comments

An online book about how ChatGPT works

ericsilberstein1.github.io
1 points·by DenisM·5 bulan yang lalu·0 comments

Agentic AI at Scale: Redefining Management for a Superhuman Workforce

sloanreview.mit.edu
2 points·by DenisM·7 bulan yang lalu·0 comments

comments

DenisM
·kemarin dulu·discuss
You seem to inhabit a hero/villaim dichotomy, and a narrative one at that. It’s not a place I wish to revisit.
DenisM
·4 hari yang lalu·discuss
For A while I was expecting that MCP will dominate, but we seem to be going in the direction of CLI being more prevalent. Can’t wrap my mind around it.
DenisM
·4 hari yang lalu·discuss
How would you compare that approach to spawning sub agents to operate high-token tools?
DenisM
·6 hari yang lalu·discuss
It stops being interesting, or even sad, after a while. People get stuck in all kinds of places, mentally. Some get unstuck eventually. It’s only sad if you have come to a counter factual belief that it could have gone better.

I went in the opposite direction - how far can I push myself to see multiple facets of a story? That is a wild ride, and it gets progressively more wild.
DenisM
·6 hari yang lalu·discuss
Yeah, there’s a Very similar comment, nearly the same words, from another guy.
DenisM
·6 hari yang lalu·discuss
In short, yes. The effort will amortize for a larger team over longer time period.

https://openai.com/index/harness-engineering/
DenisM
·6 hari yang lalu·discuss
How do employers perceive such diploma? I would try to find out before spending time or money. Did you?
DenisM
·6 hari yang lalu·discuss
It’s the diffrence between net present state and the sequence of events the lead to it, aka event sourcing.

There are pros and cons both ways.

NPS is more succinct and devoid of intermediate deviations, thus less likely to throw the agent off target.

ES otoh does contain deviations which might be salient in the future reasoning. If nothing else then to prune approaches that are known to be dead ends, but also fruitful approaches might have use especially when couple with the line of reasoning that lead to their application.
DenisM
·6 hari yang lalu·discuss
What if a tool produced an error and a retry? Is retry loop now a part of the log?
DenisM
·12 hari yang lalu·discuss
Can you share more? It’s the first I hear of lora outside research papers. Practical applications would be great to see.

Lora if effective could be a great reason to run local models.
DenisM
·21 hari yang lalu·discuss
Having gone through encryption export control I came to conclusion that preventing export of technology was never the goal.

By choke-pointing commercial efforts to export cryptographic tech the NSA got a perfect view and control lever of expertise export and transfer.

My hunch is that while deploying An algorithm is easy, deploying a system that is actually secure as a whole end to end requires a lot know how.

Bottom line it’s a bot naive to think that NSA is simultaneously very capable at being an omnipresent spy and is so stupid to not recognize that export controls have obvious holes.
DenisM
·22 hari yang lalu·discuss
> That's not a character flaw. It's a phase.

Oh dear. Must we? Half the article is like this.
DenisM
·26 hari yang lalu·discuss
did not do much better
DenisM
·27 hari yang lalu·discuss
Not a joke, actual roundabout.
DenisM
·27 hari yang lalu·discuss
Under socialism ecology did do much better. Maybe it’s not the ism that’s at play here.
DenisM
·27 hari yang lalu·discuss
Simpler still, a “minor” bit on the phone, set by parents once. All services must respect the bit in http headers, and app stores should refuse to install certain apps. No need for id check

I imagine that many parent don’t want micromanage their kids apps, this takes care of the problem.
DenisM
·bulan lalu·discuss
Did you manage to setup a discussion with the agent to reveal such assumptions? Sometimes the shave wrong unstated assumptions when contradicted by evidence, but if we’re taking about a plan for the future the evidence is thin.
DenisM
·bulan lalu·discuss
In some ways they are giving you a spec and UI mocks to implement.
DenisM
·bulan lalu·discuss
> with the hope of it giving you the right answer with the right prompt.

Consider that our ability to evaluate quality of the output is falling further behind our ability to produce it. The “right answer” is not the most likely outcome.
DenisM
·bulan lalu·discuss
Notably the feed metrics and traces into the agent. I never thought of doing that.