Jason Doggart

590 posts

Jason Doggart

Jason Doggart

@JasonDoggart

Product at Ascend

Katılım Aralık 2017
1K Takip Edilen71 Takipçiler
Aaron Francis
Aaron Francis@aarondfrancis·
They say AI is the end for developers. They say the job market is gone. They say learning to code is pointless. I don’t buy it. I think we're just getting started.
English
231
158
1.4K
272K
Jason Doggart
Jason Doggart@JasonDoggart·
@Shpigford I've liked it. The only thing I'm still missing is the cmd-t being a tab switcher (instead of just new tab)
English
0
0
0
19
Acolyte Alchemist
Acolyte Alchemist@acolytealch·
@aarondfrancis @kentcdodds You aren't building anything. AI is. It is like ordering a pizza, and they claiming you made it, just because you described what you wanted.
English
5
0
16
1.7K
Aaron Francis
Aaron Francis@aarondfrancis·
2021: it can’t even autocomplete a line 2022: it can’t even write a whole function 2023: it can’t even pass a coding interview 2024: it can’t even build an app 2025: it can’t even handle complex projects 2026: oh no
English
326
663
10.7K
698.8K
Vic 💜
Vic 💜@pattrnmatch·
I would pay hundreds for a course no older than 1 year about building a real web app from scratch with Elixir, Phoenix, LiveView, Postgres.
English
12
0
49
3K
Jason Doggart
Jason Doggart@JasonDoggart·
@aarondfrancis This came across my feed and I thought it was a joke! Can we get back to being serious about work again?
English
2
0
60
8K
Aaron Francis
Aaron Francis@aarondfrancis·
What are we even doing? This is so embarrassing
Y Combinator@ycombinator

Chad IDE (@cladlabs) is the brainrot code editor. AI coding takes 1–5 min between prompts—too long to ignore, too short to start something new.  Chad integrates your brainrot (X, IG, Stake, Tinder, etc) into your agentic coding workflow and helps to manage your context-switching. Less doom-scrolling. More shipping.

English
87
44
2.5K
358K
Jason Doggart
Jason Doggart@JasonDoggart·
@LibreChatAI - do you have an ETA on when subscriptions will be open again for code interpreter?
English
0
0
0
14
Jason Doggart
Jason Doggart@JasonDoggart·
@aarondfrancis It's pretty clearly applying less conditioning to the air, not sure where the confusion lies... 🙃
English
0
0
1
28
Aaron Francis
Aaron Francis@aarondfrancis·
It's either: • turn the temperature down • turn the fan speed down "Turn the a/c down" could mean anything! It's nothing!
Mostly Technical@MostlyTechPod

This week Ian and @aarondfrancis try to answer one of society's most pressing questions: What does it mean to "turn the air conditioning down"? Drop your answer in the replies ⬇️

English
22
0
36
10.1K
Brent Beshore
Brent Beshore@BrentBeshore·
You are born... ....with a purpose, invited into the greatest story ever told, called to co-labor in the grand adventure of bringing a little heaven to earth and imperfectly loving people. You find this deeply fulfilling. You die, and everything bad and sad becomes untrue.
Eric Jorgenson 📚 ☀️@EricJorgenson

You are born. You stare at a small square of glass, full of flashing lights, for 80 years. You find this deeply entertaining. You die.

English
26
19
263
28K
Jason Doggart
Jason Doggart@JasonDoggart·
@jerryjliu0 How does Sonnet 4 compare to GPT 4.1? I’ve found 4.1 >> Gemini 2.5
English
1
0
0
230
Jerry Liu
Jerry Liu@jerryjliu0·
How does Sonnet 4.0 compare vs. Gemini 2.5 Pro on document understanding? 👇 I’ve found Sonnet 4.0 to be much better at table parsing. Check out the screenshot below 🖼️ - I compared both models’ visual reasoning capabilities over a screenshot of a dense Caltrain schedule packed with table values. On a subset of the full schedule, Gemini 2.5 Pro gets misaligned columns while Sonnet 4.0 is actually surprisingly good at reconstructing most of the values correctly, only getting the header wrong (and a small number of other values outside of this screenshot, but far less than 2.5 Pro). Obviously it is still quite expensive and slow, and if you use the raw API endpoint on your own, you’ll get lower performance + rate-limited / content-filtered. With LlamaParse you can get optimized access to any of these models + an “auto-mode” that dynamically selects the parsing mode for the page. Check it out: cloud.llamaindex.ai/?utm_campaign=… Come talk to us if you’re interested: llamaindex.ai/contact?utm_ca…
Jerry Liu tweet media
English
5
7
97
12.3K
Derrick Reimer
Derrick Reimer@derrickreimer·
Product development in a nutshell. Theory: Listen to your customers' pain points, spot themes and patterns, come up with ideal solutions, build & ship 💪 Reality: Contend with a long-tail of one-off, esoteric use cases with occasional blips of signal rising above the noise 😵‍💫
English
4
0
37
1.4K
StripMallGuy
StripMallGuy@realEstateTrent·
How old do your kids need to be before vacation is actually relaxing, asking for a friend
English
860
57
5.5K
699K
Jason Doggart retweetledi
Mark Carney
Mark Carney@MarkJCarney·
Canada has what the world needs. Now it’s time to build — big, bold, together.
English
1.8K
1.3K
9.3K
516.7K
Josh Pigford
Josh Pigford@Shpigford·
I wish @browsercompany would sell off @arcinternet to someone who doesn’t need to make VCs a bagillion dollars. Then charge $20/mo for it. And update it. I don’t know that I’ve ever been more bummed at a company sunsetting a product.
English
68
18
1.1K
113.3K
Jason Doggart
Jason Doggart@JasonDoggart·
I want a GitHub contribution graph, but from @cursor_ai that shows me what fraction of their code was written AI. I’m looking to hire engineers who have fully embraced LLMs to write code, and seeing their history of cursor use would be a pretty good indicator (it’s hard to screen for this right now)
English
0
0
0
47