Gabor Barany

context curator, guardian of feedback loops

[Gabor Barany @GaborBarany]

missed gh-dash after moving to self-hosted forgejo, so i built one.

tea-dash: keyboard-driven terminal dashboard for gitea + forgejo. PRs, issues, notifications, CI runs. go + bubble tea, MIT.

https://t.co/HQ1jU9HvCy

[Ryan Holiday @RyanHoliday]

There's no one to perform for.

There is just work to be done and lessons to be learned, in all that is around us.

[Reads with Ravi @readswithravi]

I'm in love with this sentence:

“Forgive yourself for not knowing earlier what only time could teach.”

[Yun-Ta Tsai @yunta_tsai]

Our lifespan is a session.
Our memory is a context.
Our senses are the input stream.
Our thoughts are the reasoning steps.
Our decisions are the tool calls.
Our habits are the system prompt.
Our goals are the objective function.
Our emotions are the reward signal.
Our relationships are the shared state.
Our regrets are the residual errors.
Our growth is the fine-tuning.
Our death is the context window closing.

And whatever remains—the traces left in others—becomes the training data for the next agent.

[Claude @claudeai]

We're extending Claude Fable 5 access on all paid plans, as well as keeping Claude Code’s weekly rate limits 50% higher, through July 19.

[Gabor Barany @GaborBarany]

essential dev gear in 2026

[albs— @albfresco]

don’t worry, there will be jobs in the future

the jobs in the future:

[Gabor Barany @GaborBarany]

next time someone asks me to explain what is an agent, harness, llms etc. i'll just share this

[Anton Razzhigaev @AbstractDL]

Daily reminder what agentic harness is

[Harley Finkelstein @harleyf]

You can build the best product in the world. If nobody knows about it, it doesn't matter.

Do the work. Then tell the story.

[brexton @brexton]

The only true moat a startup can have is whether or not the founder’s got that dawg in them

[Guillermo Rauch @rauchg]

Human judgement in engineering is ironically even more crucial now. Deciding what to build. Deciding on the right architectures. Deciding whether you regenerate from scratch $$$ or reuse existing legos. Managing tech debt. You can do anything now, but you can't do everything.

[Reads with Ravi @readswithravi]

“The purpose of knowledge is action, not knowledge.”

— Aristotle

[Gabor Barany @GaborBarany]

vendor lock-in is a great problem to have. it means you actually shipped something valuable enough to be trapped by

[Gabor Barany @GaborBarany]

the ceiling on agent adoption is how fast a human can digest what the agent produced well enough to sign their name to it

[Aravind Srinivas @AravSrinivas]

The best application for models to run locally on hardware you own would be personal robots. There’s no way anyone is going to get comfortable streaming your home to a server. And when this happens, the local hardware will also become a token faucet for your digital tasks.

[Jaana Dogan ヤナ ドガン @rakyll]

Dealing with scale under a ton of ambiguity is hard. Decision making and execution slows down with success. It’s painful but is also nature’s greatest equalizer.

[Gabor Barany @GaborBarany]

> rent intelligence but own your context 💯

[Ashwin Gopinath @ashwingop]

Claude Tag is a Trojan horse.  Not because Anthropic is doing anything evil. Because the incentives are obvious.

Day one, this looks like a great feature: tag Claude in Slack, let it follow the thread, remember context, connect to tools, break down tasks, chase work, and act like a teammate.

But that is exactly the problem. The moment your AI vendor becomes a shared coworker, it stops being just a model provider. It starts becoming the place where work is interpreted, remembered, routed, and eventually executed.

That is not model lock-in. That is context lock-in. You are now renting your company back from them.

Models can be swapped. Agents can be copied. But the memory of how your company actually works is much harder, maybe impossible, to move: the Slack scar tissue, the exception paths, the customer promises, the unfinished threads, the weird workflows, the implicit owners, the “we tried that in Q2 and it failed” knowledge.

Once that lives inside one vendor’s agent layer, you are not renting intelligence anymore. You are renting your company’s operating memory.

And the pricing model makes it even more dangerous. A human coworker has a salary. Claude has unbounded tokenized activity. The more work moves through it, the more the vendor captures not just IT spend, but labor spend.

This is the enterprise bargain people will regret: Convenience now, and rapid decent into dependency.

The right architecture is simple: rent the best intelligence from whoever is best this month. OpenAI, Anthropic, Gemini, open source, whatever. But own the context layer.

Your company memory should be inspectable, permissioned, portable, and model-neutral. It should not be buried inside the same vendor that sells you the intelligence and the workflow surface.

Claude Tag is useful. That is why it is dangerous. Rent the intelligence, but own the context. Or, regret later.

[Aravind Srinivas @AravSrinivas]

Moving fast is essentially an expression of humility as you make frequent contact with reality

[Jahir Sheikh @jahirsheikh8]

Employee: 3k, 3k, 3k, 3k

Freelancer: 1k, 2k, 3k, 2k, 1k

Entrepreneur: 0, 0, 0, 0, 5k, 10k, 20k, 30k, 100k, 500k, 1M

Startup Founder: 0, 0, 0, 0, 0, 0……

[Ansh Nanda @anshnanda]

Apps won't have agents. Agent will have apps.