jalopy

This is a super helpful and productive comment. I look forward to a blog post describing your process in more detail.

This sounds very promising. Any link to more details?

Every time I read stuff like this I honestly wonder if the author is using the same tools I am.

I can have Claude Code bang out everything from boilerplate to a working prototype to a complex algorithm embedded in a very complex and confusing code base. It’s not correct 100% of the time but it’s pretty damn close. And often times it comes up with algorithms I would have never thought of initially.

These things are at least a 10x multiple of my time.

Super valuable resource - thanks!

What tools / experiments out there exist to exercise these cheaper models to output more tokens / use more CoT tokens to achieve the quality of more expensive models?

eg, Gemini 2.5 flash / pro ratio is 1 1/3 for input, 1/8 for output... Surely there's a way to ask Flash to critique it's work more thoroughly to get to Pro level performance and still save money?

Interesting tidbit:

>> In this study, high levels of these beta oscillations were associated with faster learning and more programming knowledge

This makes me think those binaural beat programs attuned to beta wave frequency might help with heavy coding sessions?

Can anyone point to studies that confirm/reject this?

This looks very interesting, however it seems to me like the critical piece of this technique is missing from the post: the implementations of getFileContext() and shouldStartNewGroup().

Am I the one missing something here?

Digging in a bit more: Love this explainer of how it's done - https://www.maptiler.com/story/oldmapsonline/

This is awesome. Love this idea. What a great way to make history more alive. I've only spent ~30s with it so far but I hope to find ways to contribute to it (content and code/different visualizations)

Great advice.

What books/resources do you suggest to follow more on this path of meditation (possibly also stoicism)?

This is great. Anyone know how hard it would be to adapt to Athena?

Do you have any open source examples (either your own or others) of simple Ruby + Sequel that are particularly elegant + productive that you could point to? Would love to see this.

I agree Ruby is the most elegant and enjoyable language to develop in.

How bad is it that one of my first thoughts was "This is a MidJourney / DALL-E embellishment"?

It's more helpful to look at a graph to see trends: https://fred.stlouisfed.org/graph/?g=XCAY

As one can see, the CPI was fairly steep during the period from Jan 2021 till June 2022; from there it has visibly flattened.

EDIT: A rolling 6 month annualized rate makes the drop pretty obvious: https://docs.google.com/spreadsheets/d/1VCEwEDWCAaWhmbosXIcD...

What is the difference between the $131 plan the the lifetime access for $29 I found here:

https://checkout.stripe.com/pay/cs_live_b1WrHao6Sw3In1xSCzhG...

Wow. So if this is universally true - that all non-macs are garbage - why is it that review sites like Notebookcheck rate some non-macs machines close to (albeit not matching) a Macbook?

For instance:

2021 Macbook Pro 16" gets a rating of 93 (https://www.notebookcheck.net/Apple-MacBook-Pro-16-2021-M1-P...)

Lenovo ThinkPad P1 G4 has a 90 rating (https://www.notebookcheck.net/Lenovo-ThinkPad-P1-G4-laptop-r...)

Are the reviewers just not evaluating machines on any real world basis? Grading on some ridiculous curve?

Any chance you'd be willing to share the spreadsheet (read-only)? That would be a great resource.

Also with their packaging tech (EMiB and Foveros) they can mix and match chips from different fabs - ie, combine P-cores from TSMC fabs with E-cores from their own (possibly older) fabs. Alder Lake is the first real stab at the "chiplet" architecture, and it seems to be a very good outing. Future iterations will only improve, and at Intel's purchase scale economics they'll be able to manufacture chiplet designs that match market needs for the highest margin or pricing pressure to squeeze competitors, if needed.

This is a "heads I win, tails I win" strategy. Give the fab business a chance to be independent and justify its massive capex and lower margin profile. Increase utilization of nodes to squeeze as much cashflow out of them as possible. If it continues to be a worthwhile cashflow endeavor, fantastic. If not, split the company and fetch a high price for a sophisticated and capable (if not #1) semi fab business.

Let the higher margin chip design business utilize whatever manufacturing process is most effective for its latest and greatest chip designs. Chip design and development won't be hamstrung by setbacks in manufacturing. Intel's scale will ensure most optimal pricing and deal terms with TSMC (if INTC doesn't use its own fab).

Along the way, there is additional upside optionality from government subsidies and support for a critical piece of infrastructure in the 21st century. Domestic fabs will be (if they aren't already) as high priority and critical to US national defense as the military hardware contractors (Boeing, Lockheed Martin, etc). That also ensures a floor to the price of the fab business should Gelsinger decide it should be sold.

Now I'm even more excited.

Replay Team - please consider charging a reasonable amount ($10/mo) for individuals/small teams. I want this to be viable as a business.

This looks fantastic. Can't wait to try it out.

I want this to succeed, so I want the company to succeed. On that note I think you guys should change up your pricing.

Seems like there's too big a gap b/w the free forever (individual) and $20/mo/user for team.

I'd love to pay for this as an individual at a smaller amount - like $10/mo - for a few extra features. Or maybe reduce the functionality of free forever.

How does this compare to Tesseract?

Going along with this: What are the latest and greatest open source speech-to-text models and/or tools out there?

Would love to hear from experienced practitioners and a bit of detail on the experience.

Thanks HN community!

If there a link to your fork?

Now that venture funding is much more widespread and entrepreneurship more celebrated (and I would argue more sophisticated), I wonder how much this advice applies.

Wouldn't a smart competitor wait to see what's working from a bootstrapped pioneer then pass them by with tons of VC cash as rocket fuel?

Does it capture the web content I view? Or just index it to retrieve the web at it's original URL later?

Don't see a chapter 3?

shells, repls, notebooks, filesystem browser, internet browser, rss, and a slew of other utilities tiled, something akin to a Bloomberg terminal, even spotify if I need music

Could you describe each of the specific packages you use to accomplish all this? I'd love to add more tools.

Wonder if the "traditional" intermittent fasting I've read about (eat during an 8 hr window, can be during the day) provides any of the same benefits.

Not eating all day long is tough; it's a lot easier when you get to count your sleep time as fasting. :)

Just took a quick look at Wanderlog and it looks awesome - exactly what I want out of a trip planning tool.

Great job!

This is the best, most informative and helpful comment I've seen. Thank you.