Joined November 2022
- Tweets 94
- Following 831
- Followers 50
- Likes 252
6 Photos and videos
Jun 8
You should assume you suck.
If you’re having a tough time with something, you’re likely just not very good at it.
You should exhaust attempts at getting better before committing all of your time to a deep analysis of the faults of the system that you’re failing in.
1
2
32
May 30
Don’t take anything for granted man, life is too unpredictable.
Death is really strange, because the loss itself isn’t what hurts. Rather, the regret of unmet plans and the pain of missing out on future conversations.
Thinking about time we should’ve spent together and won’t.
51
May 22
I prefer my definitions to be less conversational, but maybe that’s just me. Google AI overview update: we now have few shot definitions!
72
May 22
Solid read. An intuitive argument for why you shouldn’t just give up, turn off your brain, and prompt away at everything.
May 21
We’ve automated every single thing we can @every with AI agents.
And yet there’s way more human work to do than ever. We’ve gone from 4 -> 30 human employees since GPT-3.
I wrote a report on the structural reasons: how AI makes expert competence cheap, why that drives up demand for experts, and why the dynamic only intensifies as we approach AGI.
After Automation: every.to/p/after-automation
1
79
May 22
I’m convinced most of these crazy long /goal runs are just poorly optimized environment instructions. So easy for the model to work for 12 hrs if the tool calls its waiting on are CI checks (which you should probably move to be local) Most I’ve seen is 6hrs w/ a large scope goal
24
May 22
100% & adding this to our orgs review agent. No excuse now.
May 20
Fork your dependencies, trim them to only your use case, never update unless it breaks for your users. I’ve been vocal about this for 10 years. I’ve always said that updating is way riskier than latent bugs (which can be tracked and CVEs monitored).
If you are updating a dependency, it’s on you to analyze every single commit in the full transitive set of dependencies. If you dont see anything compelling, dont update!
I remember at HashiCorp once in awhile an engineer would try to update a dep or replace a DIY lib with an external one and id always ask “show me the commit we need.” Dont update for the sake of it.
Feeling pretty swell about this mentality with all the supply chain attacks happening.
60
May 21
Claude mobile with Opus 4.7 & adaptive thinking has become unusable. Refuses to think or call tools, even when I’ve explicitly asked for web searches. I can barely get tool calls to happen anymore. I am dumbfounded by the outright refusal. $200/mo ?! Wdym you won’t try?!
1
60
May 21
Seriously, when are we going to stop with these dynamic reasoning effort / auto routing attempts? They don’t work and when I ask the model to do something I want the model to try as hard as it possibly can, at least when I ask! I wish I could explicitly set the reasoning effort like I can in Claude code.
29
May 18
Agents are still pretty bad for non-coding use cases. I ran a workflow for an upcoming trip to London, selecting outfits based on my itinerary. I was really hoping that with Codex Chrome plugin it could search, evaluate, and add to cart. Only kind of works, very lazy selections
2
76
May 11
OpenAI models being bad at UI is the only thing that has me keeping my Claude subscription. Just did my wedding reception seating chart and layout with a Claude generated editor and it was pristine.
2
97
May 8
If these enterprise SaaS weren’t full of it regarding AI adoption, they’d provide ephemeral agent sandboxes of their software for safe, proper back pressure. Instead, devs have to risk nuking their only allocated dev/sandbox/staging environment anytime they run agents AFK.
80
Apr 29
There’s a category of smart people, who are constantly dismissive of anything that has received even a small amount of hype. I guess it makes them feel smart? It’s been quite something to watch these people get burned as the technology & techniques turn out to be beneficial 😂
63
Apr 27
So many new products to be built atop this. Using a complete & aesthetically sound brand guidelines GPT-Image 2 and style references produces actually premium collateral. Crazy.
Apr 27
GPT Image 2 is so good that a subscription to ChatGPT/Codex would be worth it even if you'd use nothing else.
97
Apr 24
Every time I’m in a bind, a new model release seems to bail me out. Thank God GPT 5.5 released today lmao, absolutely clutch.
45
Apr 9
So many people seem to be trying to use AI to work a lot harder, and bragging about it.
Why are you bragging about your complicated setup that requires you to work harder? Have you tried just having the models do the work well? It’s out there man. Get out of the loop!!!
28
Apr 7
Alexa is really terrible overall, but the final straw might be that occasionally, when I thank it, it lowers the volume on the device and *whispers* a contextual “you’re welcome” back to me.
27
Apr 4
Just totally radioactive. These posts are not well advised 😬
Apr 4
YC and Delve have parted ways.
I still remember the day we took our YC interview at MIT.
We’re so grateful to the community and every founder friend we’ve made.
We'll continue to support every young founder striving to make the world a better place.
120