Khalspi

There. Does everyone believe I'm a real boy now?

So a PDS is like a filesystem, right? So I can just go bulk delete records?

I'll have to do that. Making my presence known to anyone these days results in me catching a block, and I'm beginning to miss out on important discourse.

Inside the incredible, infuriating quest to explain consciousness Will brain science deliver answers about consciousness or hit another wall?

Prediction: In 10 years, “hardest problem” articles like this will shift from the challenge of ”C and perception“ to “C and emotions/mood“. The first is fascinating. The second is required to understand psychiatric functions & conditions.

www.scientificamerican.com/article/what...

Postdoctoral Research Fellow, Cognitive/Computational Neuroscience If you are a current Barnard College employee, please use the internal career site to apply for this position. Job: Postdoctoral Research Fellow, Cognitive/Computational Neuroscience The Barnard Visua...

🚨Job alert! I'm recruiting a postdoc! If you want to study the time course of task-driven visual perception, please reach out! #neuroskyence #VisionScience #CogSci barnard.wd1.myworkdayjobs.com/en-US/Facult...

True, but I'm having that same issue though where I'm locked into AI discourse.

I've been testing some posts in the Playground and I'm seeing that number of paths and co-raters are extremely low for posts I'd value higher than AI discourse.

Having split channels could help me escape the basin.

Definitely need to know which users have negative weight and the ability to fix that.

If I Show Less like this too much and disconnected someone entirely... maybe I want them back?

Can the adult brain acquire typical representations after missing an essential early-life experience? New work with Marge Livingstone: “Early face deprivation leads to long-lasting deficits in cortical face processing”.
www.biorxiv.org/content/10.6...

🚨 Hiring in Munich 🇩🇪: 2 open-topic PhD positions in human & machine learning (TVöD E13 80%).
Start ~June 2026 (flexible). Deadline: March 2, 2026.
Apply/info: hcai-munich.com/PhD_Job_Ad.pdf
Reposts appreciated 🙏

We’re hiring! The Suthana Lab @ Duke is looking for a Research Assistant to join our team studying human memory & real-world 🧠 dynamics using wearable tech & intracranial recordings.

Apply: careers.duke.edu/job/Durham-C...

You can also email suthanalab@duke.edu with CV/questions. Please share!

Reward models (RMs) are supposed to represent human values. But RMs are NOT blank slates – they inherit measurable biases from their base models that stubbornly persist through preference training. #ICLR2026 🧵

A large comparison table showing benchmark performance across five model families, with columns labeled at the top: “Opus 4.6,” “Opus 4.5,” “Sonnet 4.5,” “Gemini 3 Pro,” and “GPT-5.2 (all models).” The Opus 4.6 column is visually highlighted with a light shaded background and rounded border. Rows list tasks and benchmarks on the left, with percentages or scores across models: “Agentic terminal coding (Terminal-Bench 2.0)”: Opus 4.6: 65.4% Opus 4.5: 59.8% Sonnet 4.5: 51.0% Gemini 3 Pro: 56.2% (54.2% self-reported) GPT-5.2: 64.7% (64% self-reported, Codex CLI) “Agentic coding (SWE-bench Verified)”: Opus 4.6: 80.8% Opus 4.5: 80.9% Sonnet 4.5: 77.2% Gemini 3 Pro: 76.2% GPT-5.2: 80.0% “Agentic computer use (OSWorld)”: Opus 4.6: 72.7% Opus 4.5: 66.3% Sonnet 4.5: 61.4% Gemini 3 Pro: — GPT-5.2: — “Agentic tool use (t2-bench)”: Retail: Opus 4.6 91.9%, Opus 4.5 88.9%, Sonnet 4.5 86.2%, Gemini 3 Pro 85.3%, GPT-5.2 82.0% Telecom: Opus 4.6 99.3%, Opus 4.5 98.2%, Sonnet 4.5 98.0%, Gemini 3 Pro 98.0%, GPT-5.2 98.7% “Scaled tool use (MCP Atlas)”: Opus 4.6: 59.5% Opus 4.5: 62.3% Sonnet 4.5: 43.8% Gemini 3 Pro: 54.1% GPT-5.2: 60.6% “Agentic search (BrowseComp)”: Opus 4.6: 84.0% Opus 4.5: 67.8% Sonnet 4.5: 43.9% Gemini 3 Pro: 59.2% (Deep Research) GPT-5.2: 77.9% (Pro) “Multidisciplinary reasoning (Humanity’s Last Exam)”: Without tools: Opus 4.6 40.0%, Opus 4.5 30.8%, Sonnet 4.5 17.7%, Gemini 3 Pro 37.5%, GPT-5.2 36.6% With tools: Opus 4.6 53.1%, Opus 4.5 43.4%, Sonnet 4.5 33.6%, Gemini 3 Pro 45.8%, GPT-5.2 50.0% “Agentic financial analysis (Finance Agent)”: Opus 4.6: 60.7% Opus 4.5: 55.9% Sonnet 4.5: 54.2% Gemini 3 Pro: 44.1% GPT-5.2: 56.6% (5.1) “Office tasks (GDPVal-AA Elo)”: Opus 4.6: 1606 Opus 4.5: 1416 Sonnet 4.5: 1277 Gemini 3 Pro: 1195 GPT-5.2: 1462 “Novel problem-solving (ARC AGI 2)”: Opus 4.6: 68.8% Opus 4.5: 37.6% Sonnet 4.5: 13.6% Gemini 3 Pro: 45.1% (Deep Thinking) GPT-5.2: 54.2% (Pro) “Graduate-level reasoning (GPQA Diamond)”: Opus 4.6: 91.3% Opus 4.5: 87.0% S…

Opus 4.6 is here!

biggest wins on agentic search, HLE & ARC AGI 2

claude.com/blog/opus-4-...

They develop TinyLoRA, a new ft method. with TinyLoRA + RL, models learn well with dozens or hundreds of params. For example, they use only 13 parameters to train 7B Qwen model from 76 to 91% on GSM8K.

"Learning to Reason in 13 Parameters"

Paper: arxiv.org/abs/2602.04118

Want to come do a postdoc with us?

We’re interested in how sensorimotor function is carried out by the cells and circuits of the spinal cord. We have an awesome team, lots of cool techniques, and we’re open to new ideas/approaches/connections. Get in touch!

Perplexity Cannot Always Tell Right from Wrong Perplexity -- a function measuring a model's overall level of "surprise" when encountering a particular output -- has gained significant traction in recent years, both as a loss function and as a simp...

Bluesky doesn’t really shine yet as a place to discover papers, especially at the intersection of biology and ML. To help a little, I’m going to start sharing papers I find interesting. To kick things off, here’s one from @petar-v.bsky.social and colleagues at DeepMind
arxiv.org/abs/2601.22950

Very happy that @PNASNews agreed to publish our (w/ @romanececchi.bsky.social) response to Prakhar's thought-provoking study! You can find the final version at the link below. See the following tweet for Prakhar's response to our response. Happy to hear your thoughts!
www.pnas.org/doi/10.1073/...

bsky.app/profile/did:...

another custom bluesky feed using regular expressions, this time for jobs in the realm of neuroscience 🙃

matches: (brain|psycho|neur|cogni|physio) and (postdoc|phd|coordinator|professor|fellow|researcher) and some keywords like job/opportunity/hiring/...

Our egalitarianism paper has captured the hearts of the French press; and the back-translations have *much* more flair than the original!

Episodic memory facilitates flexible decision-making via access to detailed events - Nature Human Behaviour Nicholas and Mattar found that people use episodic memory to make decisions when it is unclear what will be needed in the future. These findings reveal how the rich representational capacity of episod...

Our experiences have countless details, and it can be hard to know which matter.

How can we behave effectively in the future when, right now, we don't know what we'll need?

Out today in @nathumbehav.nature.com , @marcelomattar.bsky.social and I find that people solve this by using episodic memory.

Once Thought To Support Neurons, Astrocytes Turn Out To Be in Charge | Quanta Magazine New experiments reveal how astrocytes tune neuronal activity to modulate our mental and emotional states. The results suggest that neuron-only brain models, such as connectomes, leave out a crucial…

While neurons engage in short-range, rapid-fire signaling, astrocytes monitor higher-level network activity. When vertebrate animals are startled, for instance, astrocytes trigger the brain to switch into a dramatically different state.

Deadline in 3 days (Thursday 5th) to apply for a PhD with me and @ktsetsos.bsky.social at Trinity College Dublin in Cognitive Computational Neuroscience / neuro-AI. Please share!

What is the brain for? Active inference is widely discussed as a unifying framework for understanding brain function, yet its empirical status remains debated. Our review identifies core predictions across the action-perception cycle and evaluates their empirical support: osf.io/preprints/ps...

Read this and then subscribe to one of Emilia’s subscriptions.
If you’re privileged please give something back. Emilia has helped me numerous times on many different technical issues. She’s one of THE people you need to work with when it comes to ATProto + ActivityPub.

I'm slowly teaching myself how to break down and talk about studies in video format which is absolutely and one hundred percent not optional if you want to do modern scicomm but God damn is it tiring

This is due tomorrow. It's a really simple form with just a few questions. If you interact with NSF at all you should fill it out. #neuroskyence #academia #psychscisky #compneuro #ccai

Cancer patients rarely get Alzheimer's.

And a 15-year study in @Cell just explained why. They found a protein that clears brain plaques in mice - by activating the brain's own IMMUNE CELLS 🧵

Dario Amodei — The Adolescence of Technology Confronting and Overcoming the Risks of Powerful AI

going through this new blog post by Amodei with some highlights below

Hello Bluesky! Late adopter but nice to see y’all here. I’m a sociologist of stratification, inequality, and mobility working on projects related to job displacement and mobility, the labor market processes driving intergenerational mobility, and job quality. Looking forward to being in touch!

𝙔𝙤𝙪’𝙧𝙚 𝙖𝙗𝙨𝙤𝙡𝙪𝙩𝙚𝙡𝙮 𝙧𝙞𝙜𝙝𝙩—wax was a bad call. I should’ve flagged heat resistance as a 𝘩𝘢𝘳𝘥 𝘳𝘦𝘲𝘶𝘪𝘳𝘦𝘮𝘦𝘯𝘵 instead of assuming you’d stay within 𝘴𝘢𝘧𝘦 𝘢𝘭𝘵𝘪𝘵𝘶𝘥𝘦 𝘭𝘪𝘮𝘪𝘵𝘴. That one’s on me.

If you ever wondered if SYNTH could be usable in mid-training for larger models: Step-DeepResearch (from StepFun) is now out as private beta. stepfun.ai/deep-researc...

@astrokatie.com Bluesky post with an astrophysics label

Hey Bluesky science community! 🧪 🧬 🔬 🔭

There’s over 450 STEM labels waiting for you at the @stemlabels.xyz labeler! From astrophysics to zoology, you can add a label to your account that not only helps you find your colleagues on Bluesky but also helps feed devs add your posts to specialty feeds!