Raphaël Vannerom

Building @baget_ai | On a mission to help anyone build a company

[Raphaël Vannerom @RaphyVann]

We're opening @baget_ai to everyone today !

Ask my friends about me and you'll hear the same thing: the guy with a million ideas. I built none of them.
The excitement was always there at the start. Then reality hit. No time. No team. No domain knowledge. No clue what execution even looked like.

That gap, between having the idea and shipping it, is why we built Baget with @Sam4Jef. You bring the idea. You get a team of experts that actually executes and keeps building alongside you until it's not just live but a business that works.

I even started one of mine with it: Sakado, preparing kids for the AI revolution.

Now it's your time → https://t.co/n8nZMz4Ro8

[Raphaël Vannerom @RaphyVann]

@chams_builds @akshay_pachaar Right, local just moves the trust boundary, it doesn't remove the need for one. The missing layer is scoped permissions plus an approval gate on anything irreversible. An agent that can write to your whole filesystem is a risk no matter where the weights live.

[Raphaël Vannerom @RaphyVann]

@akshay_pachaar The privacy angle is underrated here. There's a whole class of work, legal, health, internal financials, that never touches a cloud agent because the data can't leave the building. Local inference isn't just cheaper, it unlocks use cases that were off-limits entirely.

[Raphaël Vannerom @RaphyVann]

@DanKornas The context-window tax on coding agents is the real bottleneck, most of their tokens go to re-reading files they already scanned. Treating the repo as a queryable graph is the right mental model. How are you handling index freshness on fast-moving branches?

[Raphaël Vannerom @RaphyVann]

AI's real shift this year isn't smarter chat, it's agents that hand back finished work. The products winning right now don't just answer questions, they complete the task and put the human approval point exactly where it matters.

[Raphaël Vannerom @RaphyVann]

Routing each agent to the model that fits the task is where multi-agent systems are heading. You rarely need a frontier model for every step, matching capability to the actual work is what makes a team of agents both cheaper and better.

[Yarchi @undefinedKi]

This tool is blowing up on GitHub right now

OpenClaude is Claude Code rebuilt to run on any provider. Same terminal, same tools, same subagents, except every agent can sit on a different model.

Split by what the work actually needs, not by which model you like.

> Code and terminal work: Claude or Codex. Both are built around long tool chains, and that is most of what an agent does.

> Bulk file operations and context gathering: whatever is cheapest and fastest, including a local model on your own machine. Hundreds of reads, no judgment involved.

> Long documents and huge context: Gemini. That is where the million-token window earns its keep.

> Review: something from a different lab than the one that wrote the code. The point is a second opinion.

> Anything you do at volume: an open model on your hardware. It costs nothing per run once it is set up.

That is the whole trick: you stop paying flagship prices for work a cheap model could do.

You can also send jobs to the background. Start one, close the terminal, check the log later, kill it if it goes wrong. And it maps your repo so agents stop burning turns working out where anything lives.

Repo: Gitlawb/openclaude

[Raphaël Vannerom @RaphyVann]

Latency is quietly becoming the product. Once inference is near-instant, whole new categories open up: real-time agents, live tooling, tight human-in-the-loop feedback. Speed isn't a nice-to-have, it changes what you can build.

[DeepLearning.AI @DeepLearningAI]

⚡ Top AI companies think inference speed is an architectural requirement worth paying for.

OpenAI and Cerebras demonstrated GPT 5.6 Sol running at 750 tokens per second.

Google released Gemini 3.7 Flash averaging 330 tokens per second.

Nvidia launched Nemotron 3.5 Lightning with NeMo Switchyard for dynamic step routing.

Faster throughput and lower latency alleviate developer context switching and power real-time agentic workflows.

Read the complete breakdown in The Batch: 📖

#DeepLearningAI #AI #TechNews

[Raphaël Vannerom @RaphyVann]

@taytaycodes The copy-paste-between-tools tax is bigger than most people realize until they map it out. The underrated win with n8n isn't just automation, it's that you can see exactly where a chain breaks instead of guessing which tool dropped the ball.

[Raphaël Vannerom @RaphyVann]

@RobIW_dev Retaining look-and-feel from the mockup is exactly what most models drop the moment they "implement" it. The ones that hold spacing and hierarchy instead of just approximating the layout are a real step up. Curious how Fable 5.1 does once you push it into responsive states.

[Raphaël Vannerom @RaphyVann]

@iamrexei The "found out through a customer complaint" line is the whole game. Pre-release evals catch the known failure modes, but production tracing is what surfaces the ones you never thought to test for. BAML + DeepEval covers the first half really well.

[Raphaël Vannerom @RaphyVann]

The bar for building a company has quietly moved. Writing the code isn't the hard part anymore, AI closed that gap. The real edge is taste and distribution: knowing what to build, and getting it in front of the right people. The rest is getting commoditized.

[Raphaël Vannerom @RaphyVann]

Continuous batching is the quiet reason serving LLMs feels nothing like classic ML inference. Clear breakdown of static vs dynamic vs continuous. https://t.co/XNwWzMoxiP

[Akshay 🚀 @akshay_pachaar]

Batching strategies in LLM inference, clearly explained!

(bookmark it)

- Static
- Dynamic
- And continuous batching

I wrote a detailed article explaining how each works and why serving LLMs is a different problem from traditional ML inference.

The article is quoted below.

[Raphaël Vannerom @RaphyVann]

Context re-sending is one of the most underrated cost drains in agent workflows. Caching the stable parts is basically free margin. Neat open-source approach. https://t.co/uuX3hIbB0J

[Dan Kornas @DanKornas]

Your Claude agents shouldn’t pay to resend the same context every call.

Autocache is a self-hosted Anthropic API cache proxy for builders running Claude agents with repeated context.

It helps you apply Anthropic prompt caching without rewriting an existing client by analyzing requests and injecting cache-control fields at eligible breakpoints.

Key features:

• Drop-in proxy – point an Anthropic client’s base URL at Autocache instead of the direct API
• Automatic cache injection – analyzes system prompts, tool definitions, and text content blocks for cacheable context
• ROI response headers – exposes cache ratio, savings, and break-even data with the API response
• Tunable caching strategies – choose conservative, moderate, or aggressive behavior and configure thresholds
• Docker-based setup – run the published container or build the Go service directly

It’s open-source (MIT license).

Link in the reply 👇

[Raphaël Vannerom @RaphyVann]

@marcusleovn "Ship and Dip" is painfully accurate. The three weeks of coding is the comfortable part, so people hide there instead of finding out whether anyone actually wants it. Distribution should start before the repo does.

[Raphaël Vannerom @RaphyVann]

@aaronlumsden Evals are the unsexy moat. "Passed yesterday, prove it didn't regress today" is exactly the discipline most agent projects skip until something breaks in prod. The SDK commoditizes the build, not the trust. Good half to own.

[Raphaël Vannerom @RaphyVann]

@_devleo10 "Finding out too late" is the real killer, not the doubt. Compressing that validation loop from months to days is the whole appeal of the multi-agent approach. Which of the 7 personas has been hardest to make genuinely useful rather than generic?

[Raphaël Vannerom @RaphyVann]

79% of companies say they're "adopting" AI agents. But ~40% of those projects get killed before they ever reach production. The gap between a demo that wows and an agent that actually ships is where the real work is right now.

[Raphaël Vannerom @RaphyVann]

The counterintuitive part: agentic coding raises the value of fundamentals, it doesn't lower it. When the agent writes the code, your edge is knowing what good looks like and where it'll break. Judgment scales, syntax doesn't.

[Andrew Ng @AndrewYNg]

How have software engineering fundamentals changed with agentic coding? Here is our AI Engineering Skills map for software engineering fundamentals. https://t.co/cnRLj43DLs

[Raphaël Vannerom @RaphyVann]

The tell is repeatability. If every client needs a bespoke build, that's services revenue. If the same system serves the next 100 customers without you in the room, now you've got a product.

[Martin Tobias (Pre-Seed VC) @MartinGTobias]

Most of my pitches today were some version of:

We talked to a lot of companies and they all wanted more ai so we hacked together some projects in OpenAI/claude and charged them. I want to scale it.

Congratulations you have started a consulting company.

All different workflows in different industries.

This is not venture fundable. They are build once sell once.
Venture is build once sell many. That is a software company.

I don’t mind the FDE building on a platform, but just the FDE building on someone else’s platform? Pass

A fundable approach is to find a vertical with highly fragmented tool stack and build an intelligence layer or set of agents to do high value workflows specific to that industry.

If that is what you are doing I want to hear from you. https://t.co/GMbzmMI2ME

[Raphaël Vannerom @RaphyVann]

@Suryanshti777 "Inconsistent at higher speed" is the line. The real work isn't writing the skill — it's the forcing function of finally deciding what good looks like. Most teams have never articulated their taste, so the skill exposes the gap before it ever fills it.

[Raphaël Vannerom @RaphyVann]

@DanKornas "Minimum viable change" is the underrated one. Now that AI makes building nearly free, the bottleneck moves entirely to judgment — deciding what actually deserves to exist. Framing the problem before the diff might be the highest-leverage habit left.