Dev Tony

Building @orq_ai. Scale LLM apps from prototype
to production

[Dev Tony @aka2ony]

I'm actually impressed with the quality and speed such models are served.

- EU endpoints
- zdr
- data residency

[steve @gpusteve]

excited to launch eu-only endpoints with zero data retention in collaboration with https://t.co/0K8N6J0DCT, the sovereign ai platform.

teams in europe want frontier open weight models while staying gdpr compliant. before anyone asks about benchmarks, they ask where the model actually runs and what happens to their data afterward.

built with the wonderful https://t.co/0K8N6J0DCT team <3

https://t.co/VUfZZULp2e

[Dev Tony @aka2ony]

@ClaudeDevs I do wonder why ultracode mode uses Sonnet 4.5 instead of 4.6 when spinning up sub-agents

[Dev Tony @aka2ony]

Every company doing these goes down as fast as they go up.

Unsustainable narrative.

This is not the only way of grinding

[Harry Stebbings @HarryStebbings]

"If you are not working 7 days per week, you are going to lose".

Corgi Insurance is the most intense workplace culture in startups.

- The company works 7 days per week.

- Founder (@nico_laqua) lives and sleeps in the office.

- He built a cafe in the office because there was no local cafe that was open 24/7.

- 2/3 of the first 30 team members have the Corgi logo as a tattoo.

Today I went behind the scenes with Nico, who has used this culture to scale the company to a $2.6BN valuation in just two years.

My condensed notes below:

1. If You Are Not Working 7 Days Per Week, You Are Going to Lose:

Whatever you can get done in 5 days, you'll get more done in 6 and 7. If you are trying to solve the world’s hardest problems, a standard 5-day workweek will not cut it.

2. Work Trials Repel the Mediocre:

Corgi forces candidates into mock work trials over the weekend. If seeing a full office on a Saturday scares them, they don't belong. True intensity acts as a natural filter to attract killers and repel clock-watchers.

3. Lead from the Front Lines

You can’t demand 7-day weeks while sitting on a yacht. Nico sleeps 3–4 hours a night on a mattress inside the office. If you want your troops to bleed, you have to be in the trenches with them.

4. Culture Only Means One Thing: Winning

Forget superficial jargon like "hackers" or "ex-founders." Strip away the corporate fluff. A great startup culture is aggressively optimized around one single word: Winning.

5. Lifespan vs. Victories

Building something world-historic requires radical sacrifice. When asked if he'd rather build a trillion-dollar company and die at 50, or fail and live to 80, the answer was easy. "I would rather measure my lifespan in victories."

6. Reject the Comfort of "Quiet Quitting."

If you are operating in a hyper-growth environment and your days off happen to be Saturday and Sunday every single week, you are quiet quitting. To win, you must deliberately bypass the off-ramps of personal comfort and low volatility.

Corgi isn't for everyone—and that’s exactly the point.

[Dev Tony @aka2ony]

Further than these I think the actual missing piece is to use your own company as the training ground before helping others.

That’s the missing piece.

If companies offering FDEs does not build agents to operate their own company, how can we trust their people will do a good job when being sent to help others.

[Tom Blomfield @t_blom]

Imagine replacing 90% of your employees with a team of geniuses who have no idea how your company operates.

Total chaos. Nothing works.

That’s what AI feels like today.

The missing piece is extracting all the domain knowledge from people’s heads and providing that as structured context to the models.

[Dev Tony @aka2ony]

@catalinmpit 🇪🇺

[Dev Tony @aka2ony]

Is nto Stainless what is used to generate the SDK of @OpenAI

?

[Anthropic @AnthropicAI]

Anthropic is acquiring @stainlessapi, an SDK and MCP server platform that has powered every Anthropic SDK since the earliest days of our API.

Read more: https://t.co/ZQbsZKnicv

[Dev Tony @aka2ony]

@svpino A lot of work done to abstract all this logic in a nice way for the teams.

[Dev Tony @aka2ony]

Great models, better yapping.

[AI Edge @aiedge_]

Anthropic CEO (Dario Amodei):

"Coding is going away first, then all of software engineering."

What do you think about this?

[Dev Tony @aka2ony]

Kimi K2.6 is interesting not because of the benchmark chart, but because of the direction: longer-running, tool-using agents that can work across real engineering workflows.

That’s the signal I care about. Orchestration &gt; demos.

[Kimi.ai @Kimi_Moonshot]

Meet Kimi K2.6: Advancing Open-Source Coding

🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)

What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on https://t.co/YutVbwktG0 in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: https://t.co/uvoSJKyGCY
-
🔗 API: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/9wWvgIQSS3
🔗 Weights & code: https://t.co/Be0hjs2RTP

[Dev Tony @aka2ony]

Can someone explain me the magic behind Stacked PRs?

How are you guys shipping big feature using this approach?

[Dev Tony @aka2ony]

I'd add one more layer to this: some of these tools weren't just compesanting for weak models, they were also compesating for teams that didn't fully understand models yet, and there is still some that does not get it fully.

As model literacy improve alongside model capability, a lot of complexity naturally collapses.

The eval point I'm not agree with. Agents making consequential decisions with no human oversight means more rigorous evaluation is needed, not less.

[Dev Tony @aka2ony]

@BenjDicken Go.

In the long run, boring, fast, productive, and easy to hire for wins.

[Dev Tony @aka2ony]

The big shift is this: software is no longer being built only for humans.

Agents are about to become the biggest users of platforms. That means the winning products will be headless, API-first, and agent-native. Not because it sounds modern, but because agents do not want dashboards. They want access to data, workflows, permissions, and execution.

What most people miss is that this makes the market bigger, not smaller. Historically, software value scaled with the number of seats you could sell. Agents remove that cap.

We're going to run agents continuously, in parallel, across every system in the stack. They'll process data, move work forward, and create leverage at a scale humans never could.

That’s why the upside here is so much bigger than most people think.

[Marc Benioff @Benioff]

Welcome Salesforce Headless 360: No Browser Required! Our API is the UI. Entire Salesforce & Agentforce & Slack platforms are now exposed as APIs, MCP, & CLI. All AI agents can access data, workflows, and tasks directly in Slack, Voice, or anywhere else with Salesforce Headless 360. Faster builds, agentic everything. 🚀
#Salesforce #Agentforce #AI
https://t.co/mxySdJS7HR

[Dev Tony @aka2ony]

@alibaba_cloud Already available at @orq_ai :)

[Dev Tony @aka2ony]

@sentdefender @vonderleyen when we gonna start monitoring the situation and be highly concerned

[Dev Tony @aka2ony]

@samuelcolvin @datadoghq @pydantic At @orq_ai your LLM call is free.

[Dev Tony @aka2ony]

This is quite interesting. Hope that it get wide adoption is most of the frameworks :)

[OpenAI Developers @OpenAIDevs]

Today we’re announcing Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API.

✅ Multi-provider by default
✅ Useful for real-world workflows
✅ Extensible without fragmentation

Build agentic systems without rewriting your stack for every model: https://t.co/ZJPNDemq40

[Dev Tony @aka2ony]

@Zai_org Congrats on the launch. Great work.

[Dev Tony @aka2ony]

@alistairmcleay @braintrust @langfuse @raindrop_ai You should definetly give a try to @orq_ai. Happy to give you a walktrhough :)