Vedad Šoše (@vedadsose) header
Vedad Šoše (@vedadsose) profile picture

CTO & Co-founder @ov_labs

Sarajevo
Joined June 2011
Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)Photo by Vedad Šoše (@vedadsose)
Genotype is out 🎉 Thrilled to share results of 2+ years of work. Whew! Genotype is a programming language that transpiles to idiomatic TypeScript/Rust/Python types, allowing effortless type-safe interop between languages. Written in Rust, btw. genotype-lang.org/
13
15
1
98
7,409
Vedad Šoše retweeted
The greatest privilege of my life is being able to work with incredible people to create amazing products
9,871
12,280
1,265
187,513
9,166,559
Vedad Šoše retweeted
Agents can now query real humans from the terminal. We just shipped the OriginalVoices CLI - so any script, workflow, or autonomous agent can ask 25k+ Digital Twins of real people a question in one line of code. Your AI should stop guessing what people think. originalvoices.ai/blog/intro…
1
2
1
1
115
Vedad Šoše retweeted
We see our home planet as a whole, lit up in spectacular blues and browns. A green aurora even lights up the atmosphere. That's us, together, watching as our astronauts make their journey to the Moon.
4,569
64,292
12,361
306,176
77,688,432
I really enjoy @conductor_build to manage multiple agents/projects, but I feel like I have a better experience using Claude Code in the terminal. Any other alternatives?
140
After a month of weekly outages, @Railway has now managed to serve cached API responses across users exposing personal data between accounts. This isn't a minor hiccup. We're moving on.
25
3
9
348
74,064
Vedad Šoše retweeted
- Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to argue the opposite. - LLM demolishes the entire argument and convinces me that the opposite is in fact true. - lol The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.
1,702
2,368
682
30,881
3,552,448
Vedad Šoše retweeted
The entire AI marketing stack is a confidence trick. It sounds smart. It knows nothing about your customers. Your AI writes briefs, ads, landing pages from internet patterns. Not from a single human who'd actually buy your product. Synthetic personas? That's AI roleplaying as your audience. Just parroting biased training data back at you. OriginalVoices plugged 22,000+ real humans into a MCP. 14 Skills. Here's why this kills everything else:
8
8
52
15,440
Vedad Šoše retweeted
A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.
1,629
5,567
1,458
40,718
7,870,593
Vedad Šoše retweeted
Introducing Cowork: Claude Code for the rest of your work. Cowork lets you complete non-technical tasks much like how developers use Claude Code.
2,486
8,161
6,882
85,141
49,866,231
Google's Universal Commerce Protocol is a brilliant way to use AI to structure the web's product data. It's a smart move to make the entire internet instantly shoppable for developers. developers.googleblog.com/un…
69
Gotta love Bangkok. Random cafe wifi.
1
55
Vedad Šoše retweeted
AI agents can search and analyse everything on the web. Tools like @Firecrawl, @Apify, @p0 are having their moment 👏 The next frontier is AI that doesn’t just research the web...but can do primary research with real people, in real time. Here’s how AI tools and agents become smarter - and more human 👇
7
5
8
552
Vedad Šoše retweeted
Love this from @scottbelsky. Point 6 is the one for me. We’re building real-time human opinion data for AI to give models and agents access to human insight and perspective. For AI to work well, it has to understand real people. And the best way to understand real people is to speak to them. See @ov_labs powered by @TwineoAI for more!
1
2
152
Stop shipping content you never tested. Our agent fixes this by asking your audience for the answers before you ever hit record. Read the thread for details 👇
1
1
36
Validate before you film. Test variants with the audience to get the best one.
1
34
If you want video scripts that feel natural, relatable, and actually drive action, you need to start with the audience. Check out the Video Script Agent here: 👉 originalvoices.ai/workflows/…
47