HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Olshansky

no profile record

Submissions

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

static.googleusercontent.com
2 points·by Olshansky·mese scorso·0 comments

Reading of OpenAI's Self-Improving Tax Agents

olshansky.info
3 points·by Olshansky·mese scorso·0 comments

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

youtube.com
2 points·by Olshansky·mese scorso·0 comments

Tilt: A toolkit for fixing the pains of microservice development

tilt.dev
3 points·by Olshansky·mese scorso·0 comments

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

datasette.io
3 points·by Olshansky·mese scorso·1 comments

[untitled]

1 points·by Olshansky·mese scorso·0 comments

LM Link: Use your local models, remotely

lmstudio.ai
2 points·by Olshansky·2 mesi fa·0 comments

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

alearningaday.blog
3 points·by Olshansky·2 mesi fa·0 comments

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

github.com
6 points·by Olshansky·2 mesi fa·0 comments

GDP.pdf: A Benchmark for Parsing PDFs

surgehq.ai
1 points·by Olshansky·3 mesi fa·0 comments

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

github.com
2 points·by Olshansky·3 mesi fa·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 mesi fa·0 comments

Why every developer needs their own agent-skills

olshansky.substack.com
2 points·by Olshansky·3 mesi fa·0 comments

Core views on AI safety (March 2023)

anthropic.com
2 points·by Olshansky·3 mesi fa·0 comments

Is there a path to Gamification of Verification?

olshansky.info
2 points·by Olshansky·3 mesi fa·0 comments

A Learning a Day: Daily Posts Since May 2008

alearningaday.blog
1 points·by Olshansky·3 mesi fa·0 comments

Noagendanomeeting.net

noagendanomeeting.net
1 points·by Olshansky·3 mesi fa·0 comments

Acclaimed Physicist and Daughter Are Burying Tiny Nuclear Reactors Underground

forbes.com
3 points·by Olshansky·3 mesi fa·0 comments

Exhaustion vs. Burnout

olshansky.info
2 points·by Olshansky·3 mesi fa·0 comments

Jump VR: Realistic Wingsuit Simulator

limitlessflight.com
1 points·by Olshansky·3 mesi fa·1 comments

comments

Olshansky
·2 mesi fa·discuss
Thanks for mentioning this.
Olshansky
·2 mesi fa·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 mesi fa·discuss
This is great. Puts Rick Rubin's appearance into perspective.
Olshansky
·2 mesi fa·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 mesi fa·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 mesi fa·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 mesi fa·discuss
I've never found a Hacker News comment this insightful. Ty.
Olshansky
·3 mesi fa·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 mesi fa·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 mesi fa·discuss
Remember when OpenAI sold half of itself for $10B?
Olshansky
·5 mesi fa·discuss
https://github.com/Olshansk/postgres_for_everything/
Olshansky
·6 mesi fa·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 mesi fa·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 mesi fa·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 mesi fa·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 mesi fa·discuss
Appreciate the feedback!
Olshansky
·6 mesi fa·discuss
Appreciate you calling this out. One of my goals is definitely to grow my audience. Will stop doing so.
Olshansky
·7 mesi fa·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 mesi fa·discuss
He was actually my manager when I interned there in 2013 :)

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