30
30
30
30
GPT-5.6 Luna vs. GPT-6 Astra: Is a $1.20 Model Good Enough for Code Review?
Entelligence benchmarks GPT-5.6 Luna ($1.20/M output) against GPT-6 Astra for code review: Luna found 69 verified bugs at 3.6% of Astra's cost.
Entelligence compared GPT-5.6 Luna ($0.20/$1.20 per million tokens) against GPT-6 Astra ($10/$50) on 50 benchmark pull requests from Cal.com, Sentry, Discourse, Keycloak, and Grafana. Astra verified 92 bugs versus Luna's 69, with precision of 96% versus 74%, and Astra caught 19 of 24 security bugs while Luna found only 9. Luna cost $0.20 total versus Astra's $5.66 and reviewed faster at 23 seconds versus 36, with the widest quality gap on Keycloak authentication and permission logic (6 vs 14 verified bugs). Running both models would find 82% of the 143 verified bugs for $5.86 total.
45
30
Sakana AI Researchers Introduce PC-ALM, a Layer-Local Alternative to Backpropagation That Trains 1000-Layer Networks
Sakana AI's PC-ALM adds per-layer Lagrange multipliers to predictive coding, matching backprop on networks up to 1000 layers with layer-local updates.
Sakana AI researchers propose Augmented Lagrangian Predictive Coding (PC-ALM), a training method that keeps every update layer-local while recovering backprop-aligned credit signals. The team proves multipliers converge to exact backprop adjoints in linear networks and trains 1000-layer residual MLPs on MNIST within about 2 points of backprop accuracy. PC-ALM matched backprop across a width/depth grid from 8 to 128 on MNIST and Fashion-MNIST where standard predictive coding failed in deep, narrow networks, and improved over PC on ResNet-18 with CIFAR-10 and Tiny ImageNet. An MIT-licensed JAX reference implementation reproduces the results on CPU.
40
Most of the bugs Claude Mythos found have never been checked by a human
Echo's analysis found only 1,900 of 23,019 Claude Mythos-found vulnerabilities were externally reviewed, 90.8% held up, but the model overstated most severities.
Echo analyzed results from Anthropic's Claude Mythos Preview vulnerability sweep across 281 open-source projects, which produced 23,019 candidate vulnerabilities, of which only 1,900 were externally reviewed. Of those, 90.8% held up as real, 1,451 of 1,596 maintainer reports were acknowledged, 97 fixes landed upstream, and 88 became advisories, but 14 of the 27 CVE-assigned severity ratings mismatched independent scoring, mostly overstated. On Anthropic's SpiderMonkey benchmark, Claude Mythos turned known crashes into working code execution exploits in 72.4% of 250 trials, versus below 1% for Claude Opus 4.6. Echo cautions the reviewed sample likely was not randomly drawn, so the accuracy figure may not generalize to the other 21,119 unreviewed candidates.
62
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
ByteDance Seed's HarnessDev benchmark finds LLM-built agent harnesses trail human engineering on code and search, with only 34 of 64 revisions generalizing.
Researchers from ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI introduce HarnessDev, a benchmark that evaluates the runnable agent harness an LLM writes rather than its answers, using Creation and Evolution stages across SWE-bench Pro, Terminal-Bench 2.1, MLE-bench, EQ-Bench3, and BrowseComp (2,207 instances). Six creator models including Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek V4 Pro, Qwen 3.7 Max, and Seed 2.0 Pro were tested; Opus 4.8 posted the best average of 67.8 versus an 86.2 human-engineered reference. Self-built harnesses beat references on writing and ML experimentation but lag badly on code and search, and quality proved executor-specific: Opus 4.8 fell from 69.3 to 33.0 on SWE-bench Pro when the executor was switched to Gemini. Evolution gains were small and noisy: of 64 adjacent changes, feedback and held-out scores agreed only 34 times (53.1%), and much generated state and memory code never executed.
48
Unsolved Problem by Fields Medalist Breached by Two High School Students
Two high school students used Claude Opus 5 and GPT-5.6 Sol to help solve an open Lorentzian polynomials problem, posting a 75-page arXiv proof.
Aayush Bathija and Prince Rohatgi of Oak Park High School, mentored by UCLA postdoc Daniel Soskin, published the 75-page paper 'Bounded Ratios for Lorentzian Polynomials' (arXiv 2609.05341), solving an open problem in Fields Medalist June Huh's Lorentzian polynomial theory. The main structural theorem extends bounded coefficient-ratio characterization from quadratic to arbitrary-degree polynomials via discrete convexity conditions. The students used Claude Opus 5 and GPT-5.6 Sol for exploration and proof ideas but independently verified all arguments; the result follows an open letter from 25 Fields Medalists voicing concerns about AI's impact on mathematical rigor.
15
30
30
Axis Robotics Releases AXIS: A Browser-Based Data Engine With 207 Robot Manipulation Tasks and 50,129 Trajectories
Axis Robotics and academic partners released AXIS, a browser-based teleoperation system yielding 207 manipulation tasks and 50,129 trajectories that lifts pi0.5 to 88.8 on LIBERO-Plus.
A team from Axis Robotics, UC Berkeley, Georgia Tech, and NTU introduced AXIS, a browser-based data engine where contributors teleoperate a simulated Franka Research 3 in a MuJoCo WebAssembly frontend while GPU backends handle task generation, training, and evaluation. The released snapshot holds 207 tasks, 50,129 episodes, and 60K+ task or scene variants from more than 70,000 community contributors. Continual pretraining of pi0.5 on AXIS data raises LIBERO-Plus performance from 83.9 to 88.8, versus 57.5 for a volume-matched RoboCasa365 control; the 2.36 TB dataset is gated for non-commercial academic use.
18
MIT creates method to force AI to comply with safety rules
MIT researchers published HardFlow, a method enforcing hard safety constraints on flow-matching generative models' final outputs without retraining.
MIT researchers led by Zeyang Li and Navid Azizan developed HardFlow, a trajectory-optimization method that enforces strict, non-negotiable constraints on flow-matching generative models by checking rule satisfaction only at the final generation step. Published in IEEE TPAMI, it outperformed six rival projection and guidance methods on four simulated benchmarks including D3IL robotic manipulation, Maze2D, physical process control, and image editing. All results are simulation-only, with no independent reproduction yet reported.
25
I wrote an AI textbook — how long until AI can do it better?
AI researcher Nathan Lambert argues LLMs remain weak at long-form technical writing, questioning whether models can autonomously organize scientific knowledge for breakthroughs.
Nathan Lambert describes writing a post-training textbook, Reinforcement Learning from Human Feedback, and finds today's LLMs weak at organizing long-form technical content despite becoming superhuman at coding and math. He notes GPT 5.5 Pro found deep typos across a 200-300 page manuscript while Claude models proved more useful as editors. He argues that compressing knowledge through writing is a prerequisite for autonomous scientific insight and tempers expectations for near-term AI-driven open science.
24
30
30
Retrofitting Code Using LLMs to Support Exceptional Behavior
EXCODER combines static/dynamic analysis with LLMs to retrofit exception-handling code, achieving 85.92% pass@1 with Qwen 2.5 Coder 32B on Java benchmarks.
The paper introduces the task of retrofitting existing code with Exception Related Code (throw statements, guarding conditions, try/catch blocks) so that given Exceptional Behavior Tests pass. EXCODER performs context engineering by integrating static and dynamic program analysis output with LLMs; it was evaluated on a benchmark built from 304 methods across 75 GitHub Java projects. Combined with Qwen 2.5 Coder 32B, EXCODER achieves pass@1, 5, and 10 rates of 85.92%, 86.18%, and 86.51%, roughly 13 percentage points over baseline, and manual inspection reveals remaining limitations.
25
30
OPEN-1B: A Fully Auditable Training Run
Open-1B releases a 1B-parameter model with bitwise-reproducible training, letting independent auditors verify every step of the run on commodity hardware.
The paper introduces a 'fully auditable' tier of model transparency: every training operation is reproducible with bitwise certainty on heterogeneous commodity hardware by imposing definite ordering on GPU kernel reductions, data batch ordering, and collective communication. Because replaying a full run on one machine is infeasible, a collective verification scheme lets many independent auditors certify individual steps covering the whole run. The authors release Open-1B with its full pretraining dataset, every intermediate checkpoint, the training codebase, and an audit harness. This rules out undisclosed data, injected biases, or backdoors that proof-of-learning or proof-of-training-data techniques cannot exclude.
58
AWS puts AI vulnerability detection to the test, and false positives pile up
AWS publicly released its Deception Benchmark (14,822 samples) showing leading AI models falsely flag 41-99% of safe code as vulnerable.
AWS released its Deception Benchmark publicly, containing 14,822 samples across 16 programming languages and more than 70 CWE categories, with 9,695 scored samples split into 6,988 code-level and 2,707 environment-gated challenges. AWS evaluated 12 models from five providers using single-turn prompts and found none met its production bar of below 10% for both false-positive and false-negative rates. With direct prompting, models caught nearly all real vulnerabilities but incorrectly flagged 41% to 99% of safe code, with precision between 52% and 71%. Asking models to prove exploitability reduced false positives by 17 to 74 percentage points but raised false-negative rates to 7-44%, with models struggling most when external controls like Kubernetes Network Policies blocked apparent exploits.
55
Import AI 468: 23 RSI ideas; PostTrainBench+; and how trust and transparency interplay with AI racing
Import AI covers 23 IFP policy ideas for automated AI R&D risks and MIT/Columbia's game theory of AI racing slowdowns.
Think tank IFP published 23 policy recommendations across seven categories to help policymakers address risks from increasingly automated AI R&D. MIT and Columbia researchers released 'Racing to Ruin,' a game theory model showing that coordinated slowdowns between rival AI firms hinge on trust and transparency. The newsletter also links a short story on interacting with powerful AI systems.
35
30
Context Engineering Inside the Harness: 4 Mechanisms That Beat Context Overflow and Goal Loss on Long-Horizon Tasks
Survey of four harness mechanisms—context budgeting, compaction, todo-state, and memory—that keep long-horizon LLM agents on task across 200+ tool calls.
The article details how agent harnesses, not larger context windows, solve context overflow and goal loss on long-horizon tasks, citing Chroma's Context Rot report showing 18 LLMs (GPT-4.1, Claude 4, Gemini 2.5, Qwen3) degrade on long inputs. Concrete implementations include LangChain Deep Agents offloading tool responses over 20,000 tokens to the filesystem and truncating old tool calls at 85% window usage, and Claude Code capping auto memory at 25KB while re-reading the 5 most recently modified files after compaction. OpenAI's Responses API now offers server-side compaction via context_management with a standalone /responses/compact endpoint, which Codex uses for long-running coding tasks. Manus reports a roughly 100:1 input-to-output token ratio per ~50-tool-call task, motivating todo.md state recitation to prevent goal drift.
52
H Company Releases NeoMME: A Family of 260M and 800M Single-Tower Multimodal Encoders That Drop the Vision Tower and Causal Decoder
H Company released NeoMME, 260M/800M single-tower multimodal encoders matching 3.75B ColQwen2.5 on ViDoRe v3 while being 14.4x smaller, under Apache 2.0.
H Company released NeoMME, a family of 262,937,906- and 793,715,032-parameter bidirectional encoders that process text and raw 32x32 image patches in a single tower, pretrained via masked diffusion and released under Apache 2.0 with day-zero Hugging Face Transformers support. NeoMME-Retriever-260M reaches 0.523 nDCG@10 on ViDoRe v3, matching 3.75B-parameter ColQwen2.5 while being 14.4x smaller; the 800M model scores 0.556. Hierarchical token pooling with int8 and binary quantization shrinks late-interaction indexes from roughly 1.5 MB to 6 kB per page while retaining 95.19% of nDCG@10; text-only BEIR retrieval remains a weak spot.
20
How well do agents use test/verification techniques?
Dan Luu's eval finds coding-agent testing instructions (TDD, formal methods, PBT, skills) mostly fail to beat defaults on Zstd implementation correctness.
The author ran 26 prompt conditions plus 4 skills on a Zstd-in-Rust implementation eval using codex with GPT-5.6, testing TDD, fuzzing, property-based testing, formal methods (Lean 4, TLA+, Verus, Kani, SMT solvers) and community skills. Nothing dramatically outperformed the default no-instruction condition, which did above average; at xhigh effort, fuzzing and PBT conditions did slightly better than formal methods. Pre-registered predictions included TDD underperforming and popular test skills (ECC, Hegel, Trail of Bits) not outperforming. Results are averages of 80 runs per condition plotted against cost.
38
30
30
Controversy over OpenAI's Maths Breakthrough
OpenAI claims its internal model proved the Navier-Stokes equations 'blow up' — a Millennium Prize Problem — amid allegations it borrowed mathematicians' methods.
OpenAI announced that an internal model produced a proof, certified in the Lean proof assistant, showing the Navier-Stokes equations can 'blow up,' implying infinite fluid speeds — a claimed solution to one of the seven $1-million Millennium Prize Problems. Mathematician Tristan Buckmaster alleged OpenAI, after learning of progress by him and Anthropic employee Levent Alpöge on 'blowing up' the related Euler equations, adopted a similar 'forcing' method; OpenAI's Sébastien Bubeck denied this, saying the model independently solved Euler by different means and produced the full Navier-Stokes proof over one weekend. Mathematicians including Diego Córdoba, co-developer of the forcing approach, remain cautious, and the community is still evaluating the competing proofs.
62
30
Reward AI Releases OM-1: A Robot Policy Trained on Human Demonstrations Only, With No Teleoperation or On-Robot Data
Reward AI released OM-1, a general-purpose manipulation policy trained solely on human demonstrations from a sensorized glove, with no teleoperation or robot data.
Reward AI announced OM-1 (Omnibody Model 1), a general-purpose robot manipulation policy trained only on human demonstrations captured via Omnibody Hand, a 7-DoF wearable glove with tactile, proximity, and in-hand camera sensing. The system uses electromagnetic hand-pose tracking, cutting mean overshoot error to 9.5 mm versus 24.9 mm for visual-inertial at 67 cm/s (a 60% reduction), and reportedly learns brand-new tasks from under 30 minutes of human data. A separate RL-trained control layer runs on its own clock so policy inference latency never stalls motion, and the policy spans industrial arms, legged humanoids, and wheeled mobile manipulators. No weights, code, dataset, API, paper, or benchmark comparisons have been released, so claims are demonstration-backed only.
35
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
OpenAI-linked accounts claim roughly 10,000 AI agents produced a Navier-Stokes singularity result in 88 hours, pending mathematical verification.
OpenAI-affiliated accounts claim a system of roughly 10,000 agents, trained over about a year with multi-agent reinforcement learning, produced a finite-time singularity result related to the Navier-Stokes Millennium Problem. The claimed 88-hour runtime and 130B-token cost circulate only via social posts, and no preprint, theorem statement, or proof artifact is available. Acceptance by the mathematics community is unresolved, so the claim's epistemic status remains unknown. The roundup also notes Cognition's $48B and Mistral's $24B fundraises, GPT Image 2.5, and Meta's Muse agent relaunch.
55
How much of F-Droid is LLM generated?
A FOSS maintainer manually graded 102 F-Droid apps from the September 12, 2026 update batch, finding many show signs of LLM-generated code.
A student and FOSS app maintainer reviewed 102 apps pushed to F-Droid on September 12, 2026, assigning each a three-tier rating for likelihood of LLM-authored code (mostly AI >50%, hard to say/mostly human, no signs of AI). The heuristic relies on commit aesthetics, README and branding style, and the presence of agentic infrastructure like Claude Code or Codex, which automatically places an app in the 'mostly AI' tier. Example ratings include Amber (Nostr event signer) as mostly AI, and Aria for Misskey as showing no AI signs. The author stresses reliable detection of LLM-generated code from text alone is impossible, so ratings are approximate.
15
Hierarchical NeRF with JAX3D for Volumetric Rendering, Novel-View Synthesis, and 3D Reconstruction
MarkTechPost tutorial implements a hierarchical NeRF in JAX using jax3d volume-rendering primitives for novel-view synthesis and 3D reconstruction.
The tutorial builds an end-to-end hierarchical Neural Radiance Field using JAX, Flax, Optax, and jax3d's volume-rendering functions (sample_along_rays, volume_rendering, sample_piecewise_constant_pdf). It implements positional encoding, skip connections, separate coarse and fine networks, and view-direction conditioning with hierarchical importance sampling. Training uses JAX JIT compilation, Adam optimization, exponential learning-rate decay, and gradient clipping. Evaluation covers PSNR, depth and opacity visualization, 360-degree rendering, and marching-cubes geometry extraction.
18