Jeffrey Ling retweetledi
Jeffrey Ling
200 posts
Jeffrey Ling
@spdling
Building @cognition past @Waymo, @GoogleAI
Katılım Ekim 2016
407 Takip Edilen1.5K Takipçiler
Jeffrey Ling retweetledi
Jeffrey Ling retweetledi
Jeffrey Ling retweetledi
We've received several questions about the Opus 5 FrontierCode results, where scores decline as reasoning effort increases. In fact, the behavior is expected under the benchmark design. FrontierCode evaluates merge-ability rather than correctness alone, incorporating criteria that reflect user experience.
One such verifier is a scope criterion, which penalizes modifications to the codebase beyond what the task requires. We observe this effect across all frontier models we evaluated, though it is most pronounced in Opus 5: at higher reasoning efforts, the model shows a stronger tendency to refactor code unprompted.
English
Jeffrey Ling retweetledi
Jeffrey Ling retweetledi
Cognition is acquiring @Interaction, the makers of Poke.
If you've ever used Poke, you know why we're so excited.
English
Jeffrey Ling retweetledi
I'm looking for an AI-pilled mathematician to spend the next few weeks cracking as many conjectures as possible with us at Cognition
For an interview please solve a previously unsolved problem and tag me
You will have unlimited tokens
Jared Zoneraich@imjaredz
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
English
Little known fact: Devin is also a mathematician!
Jared Zoneraich@imjaredz
Proud to say that Devin has cracked three more unsolved problems today 1) REFUTED: Graffiti Conjecture 154 (open for ~40 years) 2) PROVED: Graffiti Conjectures 39 & 40 (~40 years) 3) REFUTED: Brandt's Regular Supergraph Problem from West's open problems list (~20 years) My methodology is explained below, but basically I showed Devin the original tweet and told it to find similar problems and crack them. The flood gates are open.
English
I've joined @cognition!
Why Cognition: extremely well thought-out end-to-end product, model-independent, obsessed with customers’ ROI instead of tokenmaxxing, and a cracked team moving at breakneck speed.
At Glean, I helped people get knowledge work done faster. Now doing the same for software engineering.
English
Jeffrey Ling retweetledi
People are surprised Cognition has only ~70 engineers. But it’s about who the 70 are
Yesterday we added @anhangz @yunpark93 from TierZero
Today were joined by @jaredpalmer
We’re building the most elite engineering team on Earth
English
Joined @cognition last month to build Devin!
Cloud agents are a huge change to the way software gets built. They're incredibly powerful already, but they need to be simpler to use and more fun to work with. We're making it so :)
If you're a Devin user, I'd love your feedback!
English
Jeffrey Ling retweetledi
Personal update: I’ve joined @Cognition to lead engineering.
I’m grateful to @asha_shar and everyone at Xbox for an amazing year.
Excited for this next chapter with @ScottWu46 and team.
English
Jeffrey Ling retweetledi
We’re thrilled to welcome @anhangz and @yunpark93 from TierZero to Cognition!
TierZero builds agents that keep your product running: handling incidents, alerts, customer issues, and reliability.
Together, we’re bringing these capabilities and more to Devin Automations.
Anhang Zhu@anhangz
Two years ago, we set out to make software self-driving. Today, TierZero is joining @Cognition to finish the job: make agents write code and keep it running. @yunpark93 and I couldn't be more excited for what's next! 🚀
English
Two years ago, we set out to make software self-driving.
Today, TierZero is joining @Cognition to finish the job: make agents write code and keep it running.
@yunpark93 and I couldn't be more excited for what's next! 🚀
English
Jeffrey Ling retweetledi
Jeffrey Ling retweetledi
Jeffrey Ling retweetledi
Devin Fusion was the first major project I worked on after joining Cognition seven weeks ago. Over the weekend, I helped add Fable to the mix. It made Devin smarter and, surprisingly, cheaper.
It was fascinating to see how much delegation styles vary across models, and how closely the best ones resemble good human management.
If this kind of work sounds interesting to you too, consider joining us at Cognition!
Joon Lee@joon_h_lee
English