Craig Tataryn

Principal Developer | Grind Software Inc. | Typescript Scala GraphQL

[Sci-Fi World Museum @hollywoodscifi]

A BLEEP at the right moment can turn anything dirty!

Whoever made this is a mad genius.

[Craig Tataryn @craiger]

@pdeva The cynic in me wonders if Claude will start producing bugs so that it can gobble up tokens in producing the bugs and diagnosing the bugs ;)

[nixCraft 🐧 @nixcraft]

Lmao

[Zed A. Shaw, Writer @lzsthw]

"Do you use Jira?"

[Craig Tataryn @craiger]

TL;DR: Anthropic copied the code that took human engineers over 37 years to build and it cost $20k + the cost of a researcher.

[Chris @ChrissGPT]

Anthropic had 16 AI agents build a C compiler from scratch. 100k lines, compiles the Linux kernel, $20k, 2 weeks.

To put that in perspective GCC took thousands of engineers over 37 years to build. (Granted from 1987 - however) One researcher and 16 AI agents just built a compiler that passes 99% of GCC's own torture test suite, compiles FFmpeg, Redis, PostgreSQL, QEMU and runs Doom.

They say they "(mostly) walked away." But that "mostly" is doing heavy lifting.

No human wrote code but the researcher constantly redesigned tests, built CI pipelines when agents broke each other's work, and created workarounds when all 16 agents got stuck on the same bug.

The human role didn't disappear. It shifted from writing code to engineering the environment that lets AI write code.

I don’t know how you could make the point AI is hitting a wall.

[Craig Tataryn @craiger]

@pdeva With those hills you’d have absolute chaos!

[Craig Tataryn @craiger]

@DZoneInc Hi, I’ve tried several times to unsubscribe from the “DZone Events” newsletter over the past few months but it appears to not be working. The sender address is DZone Events <[email protected]>

[Craig Tataryn @craiger]

@asmah2107 Apollo GraphQL Federation

[Matthew Skala @mattskala]

Today's free video on Matthew Explains looks at the "goldfish" loss function, used in the recent Apertus language models. It's supposed to prevent copyright infringement by making the model unable to reproduce word-for-word quotations. Does that work? https://t.co/GFPt51lGl2

[Craig Tataryn @craiger]

@jamesladd I’m really curious what type of input that keyboard was for 🤔

[Craig Tataryn @craiger]

I really hope the opportunity is missed for years to come. First of all it resides within a park. Cottages there are on leased land and are very modest, using a shared well to fill cisterns as needed for water. Sewage is hauled away by trucks because there's no infrastructure.

[Brent Bellamy @brent_bellamy]

The beautiful white sand beaches on Lake Winnipeg feel like a missed opportunity. Like ocean beaches, with nothing similar for thousands of kilometers, they might be a destination from across the centre of the continent if developed with quality resorts and tourist amenities.

[Matthew Skala @mattskala]

My latest video just went live, and as well as being free, it covers some points I know are of interest to people here regarding the distinctions among training, fine-tuning, and prompting.  I'm hoping it gets a lot of views. https://t.co/klLCcsCRJh

[Craig Tataryn @craiger]

@brent_bellamy Used to play arcades at that store back in the ‘80s, I think it was also a laundromat at the time too. There was also a store directly across Grey St. but it’s no longer there.

[Craig Tataryn @craiger]

@DrDisrespect Break 50 episode with DeChambeau?

[Craig Tataryn @craiger]

@DIYFractal @thunderf00t Bought almost works as well

[Craig Tataryn @craiger]

@springrod They must use the same one that Evernote does 😅

[Craig Tataryn @craiger]

@thunderf00t The piece that you examined, was it pulled from the ocean? If so, how was it dried out? I believe you had mentioned in the video that it’s hard to liberate the water once it’s absorbed. Did you have to heat it up to promote evaporation?

[Craig Tataryn @craiger]

@pdeva Sonnet does well for my purposes but you praise Opus a lot so I’m interested.

[Craig Tataryn @craiger]

I really wish more founders understood this. Also, the ability for the team to communicate effectively and understand requirements is key.

[Samuel Stroschein @samuelstroschei]

@sanjeevn72 absolute advantage of a cracked team in the age of ai!

just not 6-9 hours apart, which leads to 24-hour long iteration cycles.

ai made iterations even faster, making timezone difference even worse