Founder @ Opulentia.AI, building generally capable superagents

“Civilization advances by extending the number of important operations which we can perform without thinking about them.” — Alfred North Whitehead Opulent turns frontier models into reliable economic engines with deterministic orchestration and confidence‑aware pauses to ship finished, auditable artifacts. Bridge the gap from AI potential to production reality—read the 10‑minute Get Started guide:opulentia.ai/blog/get-starte…
1
14
1,516
Jeremy@Opulentia retweeted
We extend @cognition’s SWE-2 reward function to steer the Pareto frontier, not just improve it. SWE-2 uses S − λₑC, where λₑ is cleverly the frontier’s derivative at that effort. We show that adapting λₑ can target a desired score/cost improvement balance. See below!
22
31
319
39,614
Jeremy@Opulentia retweeted
send a swarm of capys to improve your codebase
It’s amazing you can just tell Capy coding agents to coordinate and reduce stomping on the same code paths and it just automatically injects agent to agent convos and it works without further orchestration
1
11
620
No one wins when the family feuds
We are terminating Chris Degnan for unethical conduct involving Cognition. The last few months have seen incredible progress in AI capabilities. San Francisco has flourished as new companies that solve new, more ambitious problems are finding great success. Generally, it is a wonderful time to be building. We at @FactoryAI have seen overwhelming interest in our model-agnostic coding agents and our software factory product. Our team has 10x’d in size, while our revenue has 100x’d year over year. This momentum has been unprecedented. A much larger competitor, Cognition (makers of Devin) has fallen behind us on the capabilities that matter most to customers: cost, quality, and security. Instead of competing in the market, Cognition engineers feigned interviews with us to pry information about our product. Not finding what they were looking for, Cognition has decided to throw their weight and money at people with direct knowledge of our most confidential plans. It feels as though ethics is being thrown out of the window in the AI era. People are willing to do anything, including exploiting privileged information and violating ethical boundaries. I think this is unique to our time, and I don’t think it’s right. Integrity still matters. Yesterday, I made the decision to immediately terminate Christopher Degnan’s roles as a Board Observer and Advisor to Factory, after over a year of service. Prior to this decision, Chris told me he had a casual conversation with an executive at Cognition AI. When I questioned his intentions, he reassured me that ethics aside, he had “made too much money” and was “too lazy to go work for Cognition,” which I trusted and believed. On Monday, Chris spent time advising the Factory team on a handful of confidential board-level matters. That evening, he called me to say that the conversation that was initially described as casual and one-off was actually formal and recurring. For weeks, while he sat in our board meetings and advised our leadership team, he was also confiding with executives of our largest competitor. Chris was subject to confidentiality obligations in connection with his work with Factory. We do not know the extent of the information he shared, but it puts his timely questions about our product roadmap and what the parity gap involves into a new light. It is sad to sever a relationship with someone who has been a trusted advisor - and even a close friend - for over a year. But Chris’s conduct is unacceptable to me. Trust in Board Membership is one of the sacred bonds in the Silicon Valley, one that helps the startup ecosystem thrive. With it comes an enormous responsibility. That trust was violated. Competition is good. I respect and in many cases admire our competitors. San Francisco is a beautiful, singular place where the bold and ambitious go to defy the norms and precedents of the past. But certain principles that must remain. Violating ethics to seek advantage turns what should be positive-sum into zero-sum. We all love technology. And we all love to compete. But we must hold ourselves to a higher standard. The future of software engineering comes with abundance that will impact every person on Earth. Building that future comes with immense responsibility. We must build and compete with integrity.
106
Jeremy@Opulentia retweeted
As a former theoretical physicist I can attest: You will not notice anything as you cross the event horizon. Your watch keep ticking, everything around you looks normal. For AGI, we have already crossed the event horizon. So far so good, but lots of work left to be done.
Factory CEO on why AGI is already here @matanSF is the co-founder and CEO of @FactoryAI, a $5 billion AI coding startup building Droid agents to automate the engineering process. He tells me how AI is changing the job of a software engineer and why Factory is betting on a future with many competing models. We get into how it balances model performance with token costs and why he thinks companies should avoid depending on one AI provider. We also discuss why he thinks AGI is already here, how Factory hires its own engineers, his view of the open-versus-closed AI debate, competition with companies like Cognition, and when companies should outsource to AI rather than build in-house. Timestamps: 00:00 The AI coding shift 06:10 What makes Factory different 11:32 Funding Factory’s growth 16:17 When AI writes the code 20:25 Hiring in the AI era 28:30 Betting on multiple models 32:49 Is AGI already here? 34:30 AI safety and regulation 39:36 Building a trusted AI business 41:32 The risks of model dependence 44:50 Competition and engineering’s future Links: YouTube: youtu.be/IMxtXy2SnH0 Spotify: open.spotify.com/show/3p1KZv… Substack: sources.news/p/factory-ceo-a… Thanks to the show’s premiere sponsors: @Atlassian, @meetgranola, and @mercury.
4
9
129
51,724
Jeremy@Opulentia retweeted
Introducing Mo, the world's first AI QA engineer Point it at your app and 100+ agents bug bash it in parallel. Every bug comes back with repro steps, logs, and a video In our evals vs Codex with Playwright MCP: → 3.8x more bugs → 9x more bugs per hour → half the cost per bug RT + reply "Mo" for $250 in free credits. Drop your app URL, Mo will bug bash it and DM you the report today
232
156
666
72,948
Jeremy@Opulentia retweeted
Code freeze isn’t really a thing anymore before releases and in the future the code might even be generated online per request according to some constraints.
803
175
6,547
1,086,142
Jeremy@Opulentia retweeted
2027 is the year we will see at scale autonomous revenue (profit?) generating agents / mini-companies already happening at sub scale today with lots of rough edges
298
165
4,025
268,340
Jeremy@Opulentia retweeted
One of the worst forms of brainrot AI has cultivated is pessimism about basic research, ie the idea that important work can only happen inside a frontier/neo lab and only with 10k+ GPUs, so the rest should not even bother. What a bleak way to think about science. And it's false.
90
292
2,460
231,879
Jeremy@Opulentia retweeted
This is well put. I think we'll see a reaction in the best companies against the "ship it" culture of the mid-2010s. Shipping is easy now. Creativity, judgement, differentiation, and the patience to iterate to greatness will become relatively more important.
"Sorry for the delayed response! Middling generative AI has fundamentally altered the strategic balance between offense & defense in the war for our attention, so I have chosen to ignore this messaging channel. Out beyond kino & slop, there is a field. I'll meet you there."
4
2
56
8,180
Jeremy@Opulentia retweeted
if you value intelligence above all other human qualities, you’re gonna have a bad time
852
3,015
21,528
9,508,835
Jeremy@Opulentia retweeted
What's the matter, babe? You haven't maxed out your agent subs this week. Did you get everything you ever wanted again?
59
17
876
52,178
Jeremy@Opulentia retweeted
You know, I had a cloud VM before it was cool!
8
6
138
9,157
Jeremy@Opulentia retweeted
Your agent can handle significantly more than you are currently asking of it
266
151
3,506
135,387
Jeremy@Opulentia retweeted
Just saw a sick internal demo. Development won't be the same
26
11
289
30,810
Jeremy@Opulentia retweeted
AI has shown us that agency is much rarer than we previously assumed
33
46
592
39,984
Jeremy@Opulentia retweeted
operating partner at major VC sent me a slop DM from their claw/agent. my immediate response was to prompt inject them for fun. fafo my dude
48
12
682
79,308
Jeremy@Opulentia retweeted
I don’t think Al is making software engineering easier. If anything I think it’s making it harder, as systems will continue to grow more complex and the pace at which you are expected to ship increases.
44
80
1,402
272,954
Jeremy@Opulentia retweeted
you adding a simple feature: - have more important priorities - if we fix this other thing first it'll be better - there's 3 ways to implement, unclear which is best you seeing someone else add a simple feature: lol it took them this long?
34
18
675
32,374
Jeremy@Opulentia retweeted
Several months of work went into building Devin's Cloud Mac! We had to rebuild its disk, networking, provisioning, VNC, and computer use from scratch, in Rust. Read my first X article about how it all works 😊
Article

How we built Devin's Mac

Last week we launched macOS support for Devin, extending Devin’s autonomous cloud development workflows to iOS apps, native macOS applications, and any project that depends on Apple’s development

29
39
396
137,222
Jeremy@Opulentia retweeted
introducing Craft a collection of design engineering concepts oss, free, and wip craft.gustavofior.com
81
119
2,704
150,388