Matthew Halliday @layereddelay

VP of Product @AltimateInc. Co-founder of @incorta. Passion for design, UX, data, stories, and making beautiful things. #Analytics layereddelay.com Silicon Valley Joined May 2011

Tweets

12K
Followers

2K
Following

2K
Likes

11K

Matthew Halliday @layereddelay

2 weeks ago

Data Engineers have a new job. I explain where I think the future lies for Data Engineering. Agree / Disagree? #ADE #AI #Data linkedin.com/pulse/what-196…

0 0 0 34 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@KaiXCreator Historical reasons? It was better. Now? Status.

0 0 0 55 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@Palak3312 Sonnet 4.6 with a better harness

0 0 0 29 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@Venkydotdev Talk is the code.

0 0 1 28 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@DanielSmidstrup altimate-code

0 0 1 9 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@piyush784066 6

0 0 0 23 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@KaiXCreator ... Legislation

0 0 0 17 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@pmitu And your docs are the PRD for Claude?

0 0 0 63 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@Aditya_181105 It's more the harness you use than the model. I have seen better results with the right harness with "lesser" models. Check out altimate.sh for an Open Source example which makes this clear.

0 0 0 80 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

If only people would read this blog they have a completely different vision of how to build with AI. Too many people write it off as they don't understand what needs to surround an LLM. This is the best article I've read this year on this topic. #AI #Harness altimate.ai/blog/the-corre…

0 0 1 29 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@WizzOnChain_ @MelkeyDev The point we are making is the harness is more important than the model. We intentional use the older models to showcase that. We are finsihing up using Deepseek at a fraction of the cost of the models and still scoring in the top 3.

0 0 2 19 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@garyvee Could not agree more.

0 0 0 8 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@akshay_pachaar 👏 100% That's why we dedicated our team to building a data engineering harness using the older models to win the #1 spot on the top 2 agentic data engineering benchmarks. The harness matters more than the model. Check out altimate.sh

0 0 0 40 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@elonmusk I heard they are going to ban altimate-code. altimate.sh

0 0 0 22 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

Apparently it only takes one tweet for @pmarca to follow you and one tweet to unfollow you. I wonder if he would follow you... . . . . . . and unfollow before finishing reading that same tweet? ¯\_(ツ)_/¯

0 0 0 31 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@briansolis @wapo I think we shall see a resurgence in the desire for uniquely raw human experiences. The polish will just feel too much. In some ways youtube provided that back in 2010 when people were doing covers of songs and they were getting more playtime than the originals!

0 0 2 31 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

@TerenceLeungSF @ChuckDBrooks @Nicochan33 @NancySinatra @alvinfoo @Hana_ElSayyed @MikeQuindazzi @Shi4Tech @antgrasso @PawlowskiMario @sallyeaves @NevilleGaunt @Eli_Krumova @baski_LA The noise would drive me nuts.

0 1 1 258 0

View Details

Matthew Halliday @layereddelay

3 weeks ago

How are you all using #claude -p along with worktrees to handle 8 claude sessions building simultaneously? Tell me your best tips. Also how are you going to handle June 15th's change in tokens with -p not being counted against your max plan? #Anthropic #Parallelism