Emre Coklar

Senior Consultants, AI Engineer, DSPy enthusiast, Founder. Building: &

[Emre Coklar @EmreCoklar]

@thorstenball What's the advantage? I really want to adopt cloud agents but it just creates more hassle and slows me down so I really want to know why.

[Emre Coklar @EmreCoklar]

@fullpatstack Hey just wanted to let you know your bot is posting LinkedIn content on X

[Emre Coklar @EmreCoklar]

@jukan05 All I can say is puts have been printing

[Emre Coklar @EmreCoklar]

@dbreunig gstack is getting out of control

[Emre Coklar @EmreCoklar]

@andrewmccalip @AmpCode tried this but I don't think the economics worked out

[Emre Coklar @EmreCoklar]

@MaximeRivest I feel like "fable talks a bit weird" is an understatement. I have a really hard time digesting it's outputs.

[Emre Coklar @EmreCoklar]

@irl_danB @a1zhang are RLMs in a while loops the answer everyone is searching for?

[Emre Coklar @EmreCoklar]

@neogoose_btw That's truly special. Congratulations!

[Emre Coklar @EmreCoklar]

@alexfmac

[Emre Coklar @EmreCoklar]

Truly my life goal

[Matthew Prince 🌥 @eastdakota]

@_asadmemon @pmarca No.

[Emre Coklar @EmreCoklar]

@dosco Not or now?

[Emre Coklar @EmreCoklar]

@rankintweets I can already tell I'll be turned down when the interviewer realizes I drink Coke Zero instead of Diet Coke 😩

[Emre Coklar @EmreCoklar]

@MartinShkreli It's not about model, it's about harness. Check out Warden by Sentry https://t.co/7lQmEgRuvh

[David Cramer @zeeg]

I have also open sourced the skills we used in Sentry to prove out this latest iteration.

https://t.co/CNtfq4ZqYs

Please use it responsibly. If you find something that others have missed, validate it, and send something up to bounty programs.

p.s. Mythos is FUD

[Emre Coklar @EmreCoklar]

@NoahZiems @lateinteraction Omar sensei is goated frfr

[Emre Coklar @EmreCoklar]

@badlogicgames @zeeg Never meet your heroes I guess

[Emre Coklar @EmreCoklar]

@FactoryAI Is this available with Missions?

[Emre Coklar @EmreCoklar]

@badlogicgames @GregKamradt @AJKemps @lucasmeijer But but I was promised intelligence too cheap to meter!

[Emre Coklar @EmreCoklar]

@mitsuhiko @fullpatstack I feel like this is a problem your product could evolve to solve.

[Emre Coklar @EmreCoklar]

Wow, search over 600M vectors in 10ms with 1 CPU. This is huge!

[Silvio Martinico @SilvioMartinico]

For the final refine phase, we implemented a cache-optimized Product Quantization (PQ) layout specifically tailored for late interaction.

Evaluated on ColBERTv2.0 embeddings, it results in 10 ms single-CPU retrieval on large-scale datasets (MS MARCO-v1, LoTTE Pooled).

[Emre Coklar @EmreCoklar]

@ibragim_bad @Shevan05 @agolubev13 What I find most interesting is that you found a way to make Gemini 3.1 Pro work when everyone has written it off as useless. I don't know of any other harnesses that are able to make it useful.