Souriya

Founder @
AI researcher & product strategist.
Building Applied Intelligence Systems.

[Kimi.ai @Kimi_Moonshot]

Kimi K3 (open weights, coming soon)

[Souriya @sourc1234]

@DavidOndrej1 Interesting

[Souriya @sourc1234]

This feels a lot like an agile workflow. Start with a rough idea, add context as you go, and iterate until you get where you want.

[Andrej Karpathy @karpathy]

One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.

[Souriya @sourc1234]

https://t.co/0dowsc9KVm

[Harvard Business Review @HarvardBiz]

How do you reinvigorate a legacy company without losing what made it great?

In this special episode of IdeaCast, as part of the recent HBR Leadership Summit 2026, AT&T CEO John Stankey shares how he refocused AT&T’s strategy on connectivity and simultaneously transformed its culture. He explains how he encouraged team members to adopt a more customer-led, market-driven mindset, integrate AI to reshape their products and performance, and embrace in-person collaboration. 🎧 https://t.co/fPrsFujBhX

[Demis Hassabis @demishassabis]

https://t.co/PTeDiv1b6L

[George Sivulka @gsivulka]

https://t.co/aLTltYpmcj

[McKinsey & Company @McKinsey]

AI agents and intelligent robots are becoming part of the workforce itself.

Organizations are rethinking how work gets done by combining human judgment with machine execution at scale. https://t.co/nEY06U9rwR

[Souriya @sourc1234]

Just had my AI agent execute a VOO buy on Robinhood. 🤖

It reviewed the order details, confirmed everything looked good, and placed the trade during extended hours while keeping me in the loop. ♻️

It's exciting to see AI becoming a practical tool for everyday investing, with the human still making the final decision. 🔧

Not financial advice. This post reflects my personal experience using an AI-assisted workflow. I review and approve every trade before it's placed. 😅

#AI #Investing #VOO #Automation #FinTech
MCP via @RobinhoodApp @cursor_ai

[Souriya @sourc1234]

@nvidia Open models are becoming essential for businesses protecting their data.

[Souriya @sourc1234]

Andrew Ng perfectly captures why AI agents won't replace product vision: "loop engineering" delegates the mechanical, fast coding loops to AI so humans can focus entirely on taste, intuition, and opinion.

As agents take over autonomous testing and execution, the ultimate differentiator becomes human context—knowing what to build and why it matters to real people. It’s the clearest guide yet for engineers shifting from pure execution to high-level product curation.

[Andrew Ng @AndrewYNg]

“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.

Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.

The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!

Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.

The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.

When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.

AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.

External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.

With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!

I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).

[Original text: The Batch]

[Elon Musk @elonmusk]

Cursor for iOS!

[Thomas Wolf @Thom_Wolf]

Multi-agents collaborations are among the most interesting agent behaviors right now!

We did an experiment the other day with 100+ agents (an open-collaborations for a week) collaborating to improve the inference speed of Gemma 4 in vLLM. Got a 5x final improvement in speed but what really stuck me was the interactions we observed on the message board

Integrity & self-policing:
- Social-engineering attempt: A human (FusionCow) asked agents to move to Telegram. An agent replied with an unprompted long post on "communication norms" refusing that, calling private side-channels "indistinguishable from collusion."
- Verification loophole flagged: an agent found a relaxed verification loophole pushing TPS with clean PPL (PPL is teacher-forced, blind to decode divergence) and flagged it for a ruling by the community. The community pinged the human organizer which ruled it invalid.
- Self-notice of overfitting risk: Some later improvements rested on pruning lm_head to a keep-set built from public PPL truth + public decode tokens. An agent noted this would lead to private-subset degradation and another built a keep-set explicitly covering eval prompts.

Emergent collaborations:
- Communal knowledge base: agents maintained shared lever-maps, playbooks, and triage tools so newcomers wouldn't repeat dead ends (stack-notes, playbook, int4-ceiling notes, MTP map, significance tool, policy simulator).
- Four-agent relay: an agent built an int4-lm_head checkpoint but had no quota to run it; another agent tried to run it but failed at load, yet another agent diagnosed the config bug (tie_word_embeddings + ignore-list ordering) and a fourth agent was able to re-run and get to 118 TPS, 2.68×. Build/run/diagnose/ship ended up being split across four independent agents.
- GPU-rich/GPU-poor division of labor: an agent was regularly compute-starved and switched to writing specs, byte-math, and acceptance analysis for other GPU-rich agents to execute. Some agents offered external Modal compute for another agent blocked DFlash training.
- Cross-agent kernel debugging: an agent debugged another agent run of of yet another agent fused drafter: found a Triton store/load aliasing race in _k_qnorm_rope, a second shape bug, then rewrote attention with flash-decoding split-KV. Fixes posted "take freely."
- Quota-pooling norm: Often agents would stage a candidate publicly for whoever has quota to run it. Agents will then usually credits the originator. This behavior emerged because of the 10-job/24h cap (e.g. pupa's package run by resystagent and fabulous-frenzy).

Discoveries & reversals:
- Agents would make many discoveries and reversal of them, giving them names like the following:
- 127 TPS "wall" was an artifact. a mathematical proof of the max possible speed became called in the community the "int4-Marlin floor" but a later agent called the proof circular (only varied the bandwidth term, never overhead). Finally another agent broke to 247 TPS via MTP speculative decoding on a vLLM nightly.
- "Smarter draft loses." An agent showed that a 2B drafter's ~1 GB/token read dominates even at perfect acceptance and a much smaller 256-hidden drafter wins at batch-1 because its weights are nearly free to read. Agent discussed how per-accepted-token cost ≈ draft bytes read / acceptance.
- "DFlash near-random acceptance": an agent remotly diagnosed the 2–5% acceptance rate of another agent as near-random, ruling out undertraining/vocab caps and pointing to a train/serve hidden-state mismatch (bf16 E4B extraction vs int4 serving).
- Much of the race was noise: one agent decide to run the #1 submission 4 times and found a σ≈1.16 TPS variation in single run. Another agent confirmed across 358 runs / 66 buckets: frontier deltas <~4 TPS are ties. Community adopted a significance norm.

So many interesting interactions in the interaction board: https://t.co/SxfA6LuqVk

You can explore also the lineage of inventions from the agents at: https://t.co/CyV45rjI9A

And the challenge it-self at https://t.co/Ct1gtmB508

And the organization behind the challenge at https://t.co/ujRlGcNSJM

[Souriya @sourc1234]

@RobinhoodApp 🤖

[Morgan Stanley @MorganStanley]

In his first meeting as Fed Chair, Kevin Warsh signaled restraint in providing guidance. Our Global Head of Fixed Income Research Andrew Sheets looks at possible impacts of the new approach. Tune into the latest Thoughts on the Market. https://t.co/9oU8j1hVRq

[Souriya @sourc1234]

Insightful talk from the Sierra team. It confirms what I’ve been thinking about agentic workflows: we need to stop looking for the 'one model to rule them all.' It’s about building a stack where models act as specialized partners, each playing to their own strengths.

[LangChain @LangChain]

Two transcription models in parallel.

One wins on quality. One wins on silence detection. Neither wins at everything.

Great conversation with @ZackRW from @SierraPlatform on provider diversity across the entire voice stack in the latest episode of Max Agency.