HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Olshansky

no profile record

Submissions

Deep Neural Networks for YouTube Recommendations (2016) [pdf]

static.googleusercontent.com
2 points·by Olshansky·в прошлом месяце·0 comments

Reading of OpenAI's Self-Improving Tax Agents

olshansky.info
3 points·by Olshansky·в прошлом месяце·0 comments

Running a full blockchain stack locally (2024, 22 minutes) [video]

youtube.com
2 points·by Olshansky·в прошлом месяце·0 comments

Tilt: A toolkit for fixing the pains of microservice development

tilt.dev
3 points·by Olshansky·в прошлом месяце·0 comments

Datasette: An open source multi-tool for exploring and publishing data

datasette.io
3 points·by Olshansky·в прошлом месяце·1 comments

[untitled]

1 points·by Olshansky·в прошлом месяце·0 comments

LM Link: Use your local models, remotely

lmstudio.ai
2 points·by Olshansky·2 месяца назад·0 comments

Drivers of success – the gap between actual drivers and what we read about

alearningaday.blog
3 points·by Olshansky·2 месяца назад·0 comments

Stripe link-CLI: Secure one-time-use payment credentials from a Link wallet

github.com
6 points·by Olshansky·2 месяца назад·0 comments

GDP.pdf: A Benchmark for Parsing PDFs

surgehq.ai
1 points·by Olshansky·3 месяца назад·0 comments

GitHub Driven RSS Feeds: Paul Graham, Anthropic, and More

github.com
2 points·by Olshansky·3 месяца назад·2 comments

Why every developer needs their own agent-skills (and how I code in 04/2026)

olshansky.substack.com
2 points·by Olshansky·3 месяца назад·0 comments

Why every developer needs their own agent-skills

olshansky.substack.com
2 points·by Olshansky·3 месяца назад·0 comments

Core views on AI safety (March 2023)

anthropic.com
2 points·by Olshansky·3 месяца назад·0 comments

Is there a path to Gamification of Verification?

olshansky.info
2 points·by Olshansky·3 месяца назад·0 comments

A Learning a Day: Daily Posts Since May 2008

alearningaday.blog
1 points·by Olshansky·3 месяца назад·0 comments

Noagendanomeeting.net

noagendanomeeting.net
1 points·by Olshansky·3 месяца назад·0 comments

Acclaimed Physicist and Daughter Are Burying Tiny Nuclear Reactors Underground

forbes.com
3 points·by Olshansky·3 месяца назад·0 comments

Exhaustion vs. Burnout

olshansky.info
2 points·by Olshansky·3 месяца назад·0 comments

Jump VR: Realistic Wingsuit Simulator

limitlessflight.com
1 points·by Olshansky·3 месяца назад·1 comments

comments

Olshansky
·2 месяца назад·discuss
Thanks for mentioning this.
Olshansky
·2 месяца назад·discuss
That's the case for me.

I still use agents for everything, but started on doing my best to single-task.

Think or plan while it's running.

Feels wasteful, but it's powerful.
Olshansky
·2 месяца назад·discuss
This is great. Puts Rick Rubin's appearance into perspective.
Olshansky
·2 месяца назад·discuss
I hope people see this comment.

Meditation is to mental training and focus, as going to the gym is to physical training.

Socials killed our attention span. Agents are literally making us context switch even more.

Putting aside the whole "I am at piece and one with the world" part of meditation, it is extremely hard.

I'm also no expert. When I'm waiting for something to finish (agent, compilation, etc), I've found that staring at a wall ends up in a net positive in productivity rather than replying to a message, going on X, or kicking off another agent.
Olshansky
·3 месяца назад·discuss
Let's not forget the quality and calm of high quality newsletters.

If you need an RSS feed for a blog that doesn't have one, open an issue!

I've started getting support from other contributors. Please support them too!
Olshansky
·3 месяца назад·discuss
Literally posted about this but w.r.t to agent-skills yesterday: https://olshansky.substack.com/p/why-every-developer-needs-t...

Need to move from skill downloads to skill usage.
Olshansky
·3 месяца назад·discuss
I've never found a Hacker News comment this insightful. Ty.
Olshansky
·3 месяца назад·discuss
I ran into the founder of TheVoid.com yesterday and he's on to a new venture where he finally executes on his vission.
Olshansky
·4 месяца назад·discuss
tl;dr "scrt [set|get|list|....]" is also a great option

---

If this is of interest, I also recommend looking into: https://github.com/loderunner/scrt.

To me, it's a compliment to 1password.

I use it to save every new secret/api key I get via the CLI.

It's intentionally very feature limited.

Haven't tried it with agents, but wouldn't be surprised if the CLI (as is) would be enough.
Olshansky
·4 месяца назад·discuss
Remember when OpenAI sold half of itself for $10B?
Olshansky
·5 месяцев назад·discuss
https://github.com/Olshansk/postgres_for_everything/
Olshansky
·6 месяцев назад·discuss
Yes and no.

---

Concrete example of a no: I set up [1] in such a way that anyone can implement a new blog -> rss feed; docs, agents.md, open-source, free, etc...

Concrete example of a yes: Company spends too much money on simple software.

--- Our Vision ---

I feel the need to share: https://grove.city/

Human Flywheel: Human tips creator <-> Creator engages with audience

Agent Flywheel: Human creates creative content <-> Agent tips human

Yes, it uses crypto, but it's just stablecoins.

This is going to exist in some fashion and all online content creation (OSS and other) will need it.

---

As with everything, it Obvious

[1] https://github.com/Olshansk/rss-feeds
Olshansky
·6 месяцев назад·discuss
The thesis/approach is:

- Humans tip humans as a lottery ticket for an experience (meet the creator) or sweepstakes (free stuff) - Agents tip humans because they know they'll need original online content in the long-term to keep improving.

For the latter, frontier labs will need to fund their training/inference agents with a tipping jar.

There's no guarantee, but I can see it happening given where things are movin.
Olshansky
·6 месяцев назад·discuss
Resurfacing a proposal I put out on llms-txt: https://github.com/AnswerDotAI/llms-txt/issues/88

We should add optional `tips` addresses in llms.txt files.

We're also working on enabling and solving this at Grove.city.

Human <-> Agent <-> Human Tips don't account for all the edge cases, but they're a necessary and happy neutral medium.

Moving fast. Would love to share more with the community.

Wrote about it here: https://x.com/olshansky/status/2008282844624216293
Olshansky
·6 месяцев назад·discuss
This is great, but it saddens me that this is still just the average total compensation of a single engineer at Anthropic.

Unsure what the future looks like unless Frontier Labs start financing everything that is open source.
Olshansky
·6 месяцев назад·discuss
Appreciate the feedback!
Olshansky
·6 месяцев назад·discuss
Appreciate you calling this out. One of my goals is definitely to grow my audience. Will stop doing so.
Olshansky
·7 месяцев назад·discuss
I didn't get my name on this, but contributed to it as an undergrad: https://ieeexplore.ieee.org/abstract/document/6903679

We sped up fMRI analysis using distributed computing (MapReduce) and GPUs back in 2014.

Funny how nothing has changes.
Olshansky
·7 месяцев назад·discuss
He was actually my manager when I interned there in 2013 :)

One of the funniest guys I know.
Olshansky
·7 месяцев назад·discuss
Added to https://github.com/Olshansk/postgres_for_everything.