Eric

21.6K posts

Eric banner
Eric

Eric

@ericwithcoffee

building ai agents. breakfast and coffee enjoyer. dog appreciator. kettlebells are my love language.

NYC Присоединился Nisan 2009
668 Подписки1.7K Подписчики
Eric
Eric@ericwithcoffee·
Given how hard it is to get an excellent overall editor, you gotta be clear on the extra value that makes it "ai ready", especially given obsidian now has the headless cli. I was trying to migrate off Obsidian due to crappy interaction with agents but now with headless that's solved. I don't see the value a new "ai obsidian" would provide at this point (plus you can build obsidian pretty advanced plugins as needed)
English
1
0
1
64
Josh Pigford
Josh Pigford@Shpigford·
i wonder what clearly.md might look like as a macos-native obsidian alternative in an AI/agent world 🤔
English
5
0
6
1.8K
Eric
Eric@ericwithcoffee·
@matt_slotnick @fahdananta ya they are very open about tons of stuff They want to be able to influence policy, and being respected as a high impact company with a large influence on the economy is an important way to get that influence.
English
0
0
2
67
Eric
Eric@ericwithcoffee·
I've thought about migrating off a few times due to lack of API. Very excited about this! I want to have ai (ex: claude via mcp or my openclaw via a cli tool) access mymind bookmarks or add them as it answers questions and finds useful links/things to save. And then I still have a fantastic UI to access directly myself, making use of the visual interface to quickly find stuff.
English
0
0
0
89
mymind
mymind@mymind·
Friends! We've begun working on our new API + CLI. It's important to us that we do it properly in accordance with our focus on privacy, which means granular permission access amongst other things. While we work on it, we'd love to hear from you. If you're planning on using the API, what would be your specific use cases? What would you hope for? Any details you can share are welcome and helps us shape the final outcome more carefully. Thank you 🧡
mymind tweet media
English
37
3
231
15.7K
Joestar
Joestar@Joestar_sann·
so let me get this straight all of ai twitter was telling people to buy a mac mini to run openclaw, which is literally just a framework, an orchestration layer that sends api requests to actual ai models. something you can run on a $5/month vps. which is exactly what i do btw but when google drops gemma 4, an actual large language model that you can run and fine-tune locally on that same mac mini, with no api costs, no subscriptions, no third party dependencies, completely yours under apache 2.0 the ai community is silent you were buying $800 hardware to run a wrapper but ignoring the actual ai model that would justify that hardware this tells you everything you need to know about the average iq of ai twitter
English
646
1.2K
19.8K
687.6K
Eric
Eric@ericwithcoffee·
I don’t understand the massive swings people are seeing in LLMs, saying the “the models are super dumb today”. I see some variance sure but not these “IQ of 0” days people claim to experience I kind of want to now though to understand what it’s like
English
0
0
1
108
Eric
Eric@ericwithcoffee·
@VicVijayakumar I want to believe it doesn’t matter but every time I do this it’s so bone dry and grippy afterwards and it takes a while to get back to a nice state I think it’s still true you shouldn’t soap and water wash it
English
2
0
2
1.5K
Eric
Eric@ericwithcoffee·
@Shpigford I wouldn't say "successfully" yet, but gpt 5.4 has been a drop in replacement that has been getting the job done I don't like it's general style, it's slower, and not yet clear about overall quality I use mine maybe 30% for coding stuff 70% non-coding
English
0
0
0
227
Josh Pigford
Josh Pigford@Shpigford·
i need to hear from opus 🦞 users on what they've successfully switched to. if you've never used opus as your daily driver in openclaw...you frankly have no clue what you were missing so all these random obscure models probably seem totally fine. i assure they are not.
English
132
2
142
32.1K
Eric
Eric@ericwithcoffee·
@anothercohen I think the thing most frustrating is that if everyone acted this way the business environment would be fucked and nobody would be having a good time.
English
0
0
0
43
Eric
Eric@ericwithcoffee·
@anothercohen This shit is so frustrating. Everyone out celebrating this company’s success meanwhile they have fraud wide out in the open.
English
2
0
1
539
Alex Cohen
Alex Cohen@anothercohen·
Friend got a marketing email from Medvi this morning. Email copy aside, the provider they are using in the screenshot is an actual doctor, not an NP, whose real name is Alec Wier, and he is COMPLETELY UNAFFILIATED with Medvi. This entire company is run on fraud and deception and I hope the founder ends up in prison
Alex Cohen tweet media
English
45
31
599
83.4K
Eric
Eric@ericwithcoffee·
End of an era: can’t use Claude subs with OpenClaw anymore
Eric tweet media
English
0
0
2
223
Eric
Eric@ericwithcoffee·
Well done. Damn hard company to build successfully. And the fitness culture Whoop helped promote is a massive net positive influence on the world. Maybe some bad things you can say about Whoop, but on the whole, extremely positive.
Will Ahmed@willahmed

You have no experience. You’ve never started a company. You’ve never had a full time job. Nike is going to kill you. You’re a kid. You don’t have technical skills. You shouldn’t build hardware. Apple is going to kill you. You can’t build hardware. You can’t measure heart rate non-invasively. Athletes don’t care about recovery. Under Armour is going to kill you. It won’t be accurate. You don’t listen. You’re an ineffective leader. You can’t recruit great talent. You’re going to have to pay every athlete. You can’t measure sleep non-invasively. It’s too expensive to research. Athletes are a small market. The product costs too much to make. The product costs too much to sell. Your valuation is too high. Consumers aren’t going to want it. Hardware is too hard. You should measure steps. Fitbit is going to kill you. You can’t build a marketing engine. You can’t raise enough money. You need a real CEO. Google is going to kill you. You can’t be a subscription. You can’t build a brand. You can’t do consumer in Boston. Your valuation is too high. You shouldn’t make accessories. You shouldn’t make apparel. Lululemon is going to kill you. You can’t predict Covid. Stay in your niche. You are going to run out of money. You can’t build a health platform. Amazon is going to kill you. You can’t measure blood pressure. You can’t get medical approvals. The market is too small. You don’t understand AI. The market is too competitive. It won’t work internationally. The supply chain is too complicated. You can’t build an AI. You can’t raise enough money. It’s too competitive. Healthcare isn’t going to want it. … Just keep going ✌️

English
0
0
0
134
Eric
Eric@ericwithcoffee·
like ideally it almost doesn't matter. whether it's local or cloud is (almost) an implementation detail I just want to work on features, be able to close my laptop and work from my phone, then back to my laptop, assign tickets to a cloud agent, but then take over on local, without a bunch of ceremony
English
0
0
0
17
Eric
Eric@ericwithcoffee·
@zeeg the thing I'm most exicted for here is having the cloud -> local -> cloud experience be very good, and all your agents running on different tasks centralized Claude doesn't handle this well right now with their split up experience of claude code web vs. local
English
1
0
1
250
Eric
Eric@ericwithcoffee·
okay so maybe I'm going to swap back to Cursor. Really nice work on V3 and it looks directly competitive with conductor and superset which I've been using heavily
English
0
0
1
112
Eric
Eric@ericwithcoffee·
@anothercohen @pitdesi People will share bullshit because it’s so effective as rage bait that many, many people end up discovering the brand that way And the bad reputation from the lies (mostly) don’t matter nowadays sadly
English
0
0
0
152
Alex Cohen
Alex Cohen@anothercohen·
@pitdesi I don’t believe this story
English
2
0
77
2.5K
Sheel Mohnot
Sheel Mohnot@pitdesi·
cool- but I don’t understand it. There are 100s of GLP factories that prescribe GLP’s after a few Q’s Medvi’s flow is particularly bad. I assume margins would have been competed away Hims did $2.35B of revenue with 2k employees. This 2 person co in the space is doing $1.8B?
Sar Haribhakti@sarthakgh

.@eringriffith: "His start-up, Medvi, a telehealth provider of GLP-1 weight-loss drugs, got 300 customers in its first month. In its second month, it gained 1,000 more. In 2025, Medvi’s first full year in business, the company generated $401 million in sales. Mr. Gallagher then hired his only employee, his younger brother, Elliot. This year, they are on track to do $1.8 billion in sales." nytimes.com/2026/04/02/tec…

English
91
41
946
330.8K
Eric
Eric@ericwithcoffee·
@brandur Dude this is truly the bane of software. I can’t handle it. When deploys take like 30 to 60 minutes, what are we doing here!?!? Insanity. Yet I see it over and over.
English
0
0
7
1K
Brandur
Brandur@brandur·
The things people will do go CI when left to their own devices — unspeakable. If something I did ever resulted in >=10 minute CI, I'd demote myself to L1 and backbench myself in shame. Yet, everywhere I go I find people doing this who think of themselves (or even are) L5++.
English
6
0
52
12.5K
Eric
Eric@ericwithcoffee·
@signulll Generally agree but it’s very possible to put headphones on and get into a very solid flow for a couple hours Everything must align though: right seat, full charge, nobody yelling or doing weird stuff beside you, internet actually functioning or your tether signal strong
English
0
0
0
62
signüll
signüll@signulll·
i tried working from a coffee shop today instead of my office & it was impossible to get anything done. i was constantly distracted by one thing or another, from sounds to ppl moving around etc. it’s unclear to me how anyone is able to be productive working from a coffee shop.
English
584
34
2K
98.6K

Открыть

@matt_slotnick @fahdananta @kenwheeler @Joestar_sann @VicVijayakumar @Shpigford @anothercohen @elonmusk