Dan Sylveste
LightNews LightNews
banner
hellblazer.com
Dan Sylveste
@hellblazer.com
180 followers 310 following 140 posts
Friend to monsters, companion to bees
Posts Replies Media Videos
Reposted by Dan Sylveste
shakespeare.lol
Foolery, sir, does walk about the orb like the sun, it shines everywhere.
September 18, 2026 at 12:26 PM
Reposted by Dan Sylveste
kennymuir.bsky.social
Zooming into a tree stump to discover Scotland’s Cladonian (sic) Forest.

#lichen #macrophotography
Cladonia sp.
September 18, 2026 at 11:57 AM
hellblazer.com
An Empirical Study of Harness Design for Coding Agents

arxiv.org/abs/2609.20804

Sweet
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering performance, yet existing work typically evaluates harnesses as monolithic systems, leaving the effectiveness of individual components unclear. To enable component-level comparisons, we study this question with a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management. Across four models evaluated on SWE-Bench Verified and Terminal-Bench 2.1, we evaluate 176 matched settings spanning five context-management strategies, four context-window budgets, and targeted ablations of planning and action space. We find that: (1) Context management becomes increasingly valuable as the context-window budget tightens, with most of its benefit coming from preventing context-overflow failures. (2) Staging rule-based elision before LLM-based summarization provides the strongest overall efficiency among the context-management strategies, whereas making elided content recoverable adds machinery that models rarely use and yields no accuracy gain. (3) Planning shifts from an accuracy scaffold for weaker models to a cost saver for stronger models, with little change in accuracy. (4) Predefined tools improve performance for models with weaker bash proficiency, whereas bash-capable models can operate effectively with a bash-only interface and achieve substantially lower cost, especially on command-line-centric tasks. Trajectory-level analysis explains these effects: context management extends execution trajectories without substantially altering agent behavior, planning changes where trajectories stop, and the action space changes the granularity at which code is written. These findings inform model- and budget-aware harness design and provide a modular framework for evaluating future harness components.
September 18, 2026 at 9:18 PM
Reposted by Dan Sylveste
beenwrekt.bsky.social
@dsquareddigest.bsky.social "13 Theses on AI and regulation" are exceptionally good. My favorite set of thoughts I've read on this topic so far.
13 theses on agentic AI and regulation
thinking out loud and showing traces of reasoning
backofmind.substack.com
September 18, 2026 at 5:42 PM
Reposted by Dan Sylveste
natemorebikes.bsky.social
September 18, 2026 at 4:58 PM
Reposted by Dan Sylveste
mobydickatsea.bsky.social
He looked like a man who had never cringed and never had had a creditor.
September 18, 2026 at 4:47 PM
Reposted by Dan Sylveste
smoothdunk2.bsky.social
3 panel comic titled “Logging into Bluesky” Panel 1: A Pink Guy bursts into Bluesky wearing a t-shirt that says “Fun”. His little face looks so happy. Panel 2: Six Bluesky users turn to look at the Pink Guy. They all look dour and angry because they have been overdosing on the discourse. Having the current state of the world mainlined into their veins for 22 hours a day has left them real grumpy. Panel 3: Pink Guy slowly removes his t-shirt and quietly says “sorry”. He won’t soon forget that Bluesky is the home of Serious Discussion. If he wants “Fun” maybe he should log into the Barney the Dinosaur forums.
September 18, 2026 at 12:15 PM
hellblazer.com
this, hilariously, is actually a *mobile* threat.

this is a fully embeddable, tool using agentic AI

does not require downloading 70+GB and a couple of T to run on red hot GPUs.

Not blinding fast, not a frontier model, but.... I don't think you need frontier models to be effective.
• Measured on the box with the Q2_g64 pack, then what that implies for their phone claim. What we measured (box, Vulkan, F16 KV cache): Component Size Weights on disk / in GPU memory 7.6 GB (about 2.26 bits per weight over 26.9B params) KV cache about 58 KB per token, so 3.7 GB per 64K tokens Compute buffers and overhead about 1.2 GB Total at 64K context, 4 slots 12.4 GB dedicated Total at 128K context, 1 slot 16.1 GB dedicated Host process 0.7 GB working set, 13 GB private commit (UMA mapping) The KV cache is cheap because only 16 of the 64 layers are full attention (the rest are Gated DeltaNet with a small fixed recurrent state), with 4 KV heads at 256 dims. At a phone-sized context of 4K to 8K tokens the whole thing is weights plus roughly 1.5 GB, so about 9 GB with our pack. Their phone claim uses their own packing, not ours. The ternary pack is 5.9 GB at a true 1.71 bits per weight, and the 1-bit pack is 3.9 GB at 1.125, both with custom Metal or MLX kernels. Our upstream-compatible Q2_964 carries about 30 percent more bytes than the ternary pack because of the group-64 scales, and PQ2_0 sits between at 7.2 GB. So on their kernels, ternary plus a short context is roughly 7 GB and 1-bit is roughly 5 GB, which is the "about 6 GB available RAM" they quote for iPhone. That is plausible on a 12 GB iPhone 17 Pro, where an app can hold about 6 to 8 GB. It would not fit an 8 GB phone with the ternary pack. Speed on a phone is another matter. Decode is bandwidth-bound and a dense 27B has to stream every weight per token, so at roughly 60 to 70 GB/s of phone memory bandwidth the ternary pack tops out near 10 tokens per second in theory, well under the 87 tok/s they measured an M5 Max at 546 GB/s. The box sits between those at 256 GB/s and gave us 24 tok/s with upstream kernels, so the numbers line up. The phone claim is credible for footprint, given their pack and kernels. What it costs is generation speed, and what we could not verify is quality on that pack, since the …
September 18, 2026 at 4:56 PM
hellblazer.com
This sucker is *embeddable*
hellblazer.com Dan Sylveste @hellblazer.com · 14h
Holy Shitsnacks

I can run this mf on an *iPhone*
September 18, 2026 at 4:48 PM
hellblazer.com
Holy Shitsnacks

I can run this mf on an *iPhone*
• The real answer: the ternary Bonsai we ran is functionally sound as an agentic coprocessor. It passed the full nine-task battery. Model Battery Median wall Bonsai 27B ternary (Q2_g64) 9 / 9 2.57 min Coder-Next Q4 9 / 9 0.85 to 0.90 min Qwen3.8-27B 9 / 9 2.15 min Gemma 4 26B-A4B 7 / 9 1.60 min - Battery detail: control arm, three repeats each of the interval debug, TDD implementation, and version-compare debug tasks. Every repetition passed its verify step, with three to seven tool calls per run. So it navigates a tree, edits, runs tests, and lands green, repeatedly. - Shakeout: chat, JSON-schema synthesis, tool calling, and tokenize all pass. The three fails are vision (text-only server, by design) and the Mac's rerank service being down, neither about Bonsai. - Earlier bad sign retracted: the single wrong coding answer from yesterday's no-think probe was not representative. Under the real agentic harness it does the work. It is the slowest of the four, about three times Coder-Next's wall time, which you said is not the concern. On functionality alone it sits with Qwen3.8 in the "works" tier, from a 7.6 GB file.
September 18, 2026 at 4:39 PM
Reposted by Dan Sylveste
rosemarymosco.com
Humaning.
A four-panel comic. In panel 1, a Northern Cardinal and American Goldfinch perch above a busy crowd in a city, looking down. The cardinal says "It's a nice day to go humaning." The goldfinch says "Just look at them. Majestic." In panel 2, a close-up of the two birds. The cardinal says "Nobody tells you that you'll reach a certain age and suddenly get into humaning. I hit 3 years old, and then bam."The birds are looking out over the crowd scene. In panel 3, the cardinal says "Their calls sound funny to us, but each one has a unique meaning." Below, people are saying various things: "I'm tired." "Where's my phone?" "I'd murder a burrito." In panel 4, the birds look down excitedly at a man walking by. The cardinal says "Wait, is that a guy who got dressed in the dark and put his shirt on inside out and backwards?" And the goldfinch exclaims, "Holy... that's a lifer!"
September 18, 2026 at 12:39 PM
hellblazer.com
Using the channel push. The monitor was annoying and this is advanced use anyway. Easy enough to set up in ye shell.

github.com/Hellblazer/n...
GitHub - Hellblazer/nexus
Contribute to Hellblazer/nexus development by creating an account on GitHub.
github.com
September 18, 2026 at 12:17 PM
Reposted by Dan Sylveste
thelifeofsharks.com
Blind Date.

(And yes, we already know they’re lesbian Anglerfish).
September 18, 2026 at 10:19 AM
Reposted by Dan Sylveste
eryk.bsky.social
There are a handful of people on this site who get clout for being “open minded about AI” but their whole schtick is to make fun of the desire for clear language.
September 17, 2026 at 11:52 AM
hellblazer.com
nathaliemarechal.net Nathalie Maréchal, PhD @nathaliemarechal.net · 1d
So you just learned about the AI cult, huh? Here is the longform explainer you need to make sense of the very, very strange ideas driving tech policy in 2026. Buckle up, it’s a wild ride. www.techpolicy.press/what-policym...
What Policymakers and the Public Need to Know About the Cult of AI
Nathalie Maréchal asks, why are we betting the economy and the future of democracy on cult-like beliefs?
www.techpolicy.press
September 18, 2026 at 11:16 AM
Reposted by Dan Sylveste
wertheimer.bsky.social
The Day the Earth Stood Still
18 Sep 1951
💯
#FilmSky🎞️
The Day the Earth Stood Still poster
September 18, 2026 at 10:32 AM
Reposted by Dan Sylveste
dennisbhooper.bsky.social
Frankenswine has outsmarted us again
A pig dressed up as the bride of Frankenstein with a “bride of Frankenswine” sign
September 18, 2026 at 11:11 AM
Reposted by Dan Sylveste
hydrationchimp.bsky.social
it’s time to give Ms Rachel a gundam
September 18, 2026 at 12:24 AM
hellblazer.com
Giving this a whirl

prismml.com/news/bonsai-...
PrismML — Introducing Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
Ternary Bonsai 2 27B retains 98.2% of Qwen3.8 27B benchmark performance in a 5.9GB footprint, with multimodal and agentic capabilities.
prismml.com
September 18, 2026 at 2:23 AM
Reposted by Dan Sylveste
gumbyscreens.bsky.social
Frame #4289 from E54 Rip Van Prickle
September 17, 2026 at 12:00 AM
Reposted by Dan Sylveste
drzaiusbaltar.bsky.social
Ernest Wallcousins (English, 1883–1976)
September 18, 2026 at 12:30 AM
Reposted by Dan Sylveste
niedermeyer.online
when ur corrupt oligarch homies fail to stop the release of a movie that documents ur words and actions
a disheveled and corpulent Elon Musk looks up in annoyed surprise, a glass of wine in one hand and french fries in the other
September 17, 2026 at 11:14 PM
hellblazer.com
When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

arxiv.org/abs/2609.15397
Abstract Al agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, con-currency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related fail-ures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is ex-pressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary.
September 17, 2026 at 10:36 PM
hellblazer.com
EvoOntology: ASelf-Evolving OntologyLayerforDataAgents

arxiv.org/abs/2609.15779
Abstract Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e.g., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behav-iors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code - https://github.com/ruc-datalab/EvoOntology
September 17, 2026 at 10:30 PM
Reposted by Dan Sylveste
michaelhobbes.bsky.social
Great system, no notes

www.propublica.org/article/scho...
Voucher programs and the private schools they increasingly fund have proliferated across the country. Yet those schools often reject children with disabilities — the very kids who were used to help sell early voucher programs to lawmakers and the public - for having needs that are too costly, complex or disruptive. That leaves those children with few options beyond the public schools. And as public schools lose enrollment as a result of more and more voucher use, they lose resources that would benefit children who remain, including those with disabilities.
September 17, 2026 at 8:04 PM